Steven Jens Jorgensen - Academia.edu (original) (raw)
Papers by Steven Jens Jorgensen
2020 IEEE International Conference on Robotics and Automation (ICRA), 2020
We present a method that finds locomanipulation plans that perform simultaneous locomotion and ma... more We present a method that finds locomanipulation plans that perform simultaneous locomotion and manipulation of objects for a desired end-effector trajectory. Key to our approach is to consider a generic locomotion constraint manifold that defines the locomotion scheme of the robot and then using this constraint manifold to search for admissible manipulation trajectories. The problem is formulated as a weighted-A* graph search whose planner output is a sequence of contact transitions and a path progression trajectory to construct the whole-body kinodynamic locomanipulation plan. We also provide a method for computing, visualizing and learning the locomanipulability region, which is used to efficiently evaluate the edge transition feasibility during the graph search. Experiments are performed on the NASA Valkyrie robot platform that utilizes a dynamic locomotion approach, called the divergent-component-of-motion (DCM), on two example locomanipulation scenarios.
2020 IEEE International Conference on Robotics and Automation (ICRA), 2020
We present a method that finds locomanipulation plans that perform simultaneous locomotion and ma... more We present a method that finds locomanipulation plans that perform simultaneous locomotion and manipulation of objects for a desired end-effector trajectory. Key to our approach is to consider a generic locomotion constraint manifold that defines the locomotion scheme of the robot and then using this constraint manifold to search for admissible manipulation trajectories. The problem is formulated as a weighted-A* graph search whose planner output is a sequence of contact transitions and a path progression trajectory to construct the whole-body kinodynamic locomanipulation plan. We also provide a method for computing, visualizing and learning the locomanipulability region, which is used to efficiently evaluate the edge transition feasibility during the graph search. Experiments are performed on the NASA Valkyrie robot platform that utilizes a dynamic locomotion approach, called the divergent-component-of-motion (DCM), on two example locomanipulation scenarios.
2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids), 2018
We propose a methodology for dynamically balancing passive-ankled bipeds and full humanoids. As d... more We propose a methodology for dynamically balancing passive-ankled bipeds and full humanoids. As dynamic locomotion without ankle-actuation is more difficult than with actuated feet, our control scheme adopts an efficient wholebody controller that combines inverse kinematics, contactconsistent feed-forward torques, and low-level motor position controllers. To understand real-world sensing and controller requirements, we perform an uncertainty analysis on the linearinverted-pendulum (LIP)-based footstep planner. This enables us to identify necessary hardware and control refinements to demonstrate that our controller can achieve long-term unsupported dynamic balancing on our series-elastic biped, Mercury. Through simulations, we also demonstrate that our control scheme for dynamic balancing with passive-ankles is applicable to full humanoid robots.
2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids), 2018
We propose a methodology for dynamically balancing passive-ankled bipeds and full humanoids. As d... more We propose a methodology for dynamically balancing passive-ankled bipeds and full humanoids. As dynamic locomotion without ankle-actuation is more difficult than with actuated feet, our control scheme adopts an efficient wholebody controller that combines inverse kinematics, contactconsistent feed-forward torques, and low-level motor position controllers. To understand real-world sensing and controller requirements, we perform an uncertainty analysis on the linearinverted-pendulum (LIP)-based footstep planner. This enables us to identify necessary hardware and control refinements to demonstrate that our controller can achieve long-term unsupported dynamic balancing on our series-elastic biped, Mercury. Through simulations, we also demonstrate that our control scheme for dynamic balancing with passive-ankles is applicable to full humanoid robots.
ArXiv, 2018
When mobile robots maneuver near people, they run the risk of rudely blocking their paths; but no... more When mobile robots maneuver near people, they run the risk of rudely blocking their paths; but not all people behave the same around robots. People that have not noticed the robot are the most difficult to predict. This paper investigates how mobile robots can generate acceptable paths in dynamic environments by predicting human behavior. Here, human behavior may include both physical and mental behavior, we focus on the latter. We introduce a simple safe interaction model: when a human seems unaware of the robot, it should avoid going too close. In this study, people around robots are detected and tracked using sensor fusion and filtering techniques. To handle uncertainties in the dynamic environment, a Partially-Observable Markov Decision Process Model (POMDP) is used to formulate a navigation planning problem in the shared environment. People's awareness of robots is inferred and included as a state and reward model in the POMDP. The proposed planner enables a robot to change...
ArXiv, 2018
When mobile robots maneuver near people, they run the risk of rudely blocking their paths; but no... more When mobile robots maneuver near people, they run the risk of rudely blocking their paths; but not all people behave the same around robots. People that have not noticed the robot are the most difficult to predict. This paper investigates how mobile robots can generate acceptable paths in dynamic environments by predicting human behavior. Here, human behavior may include both physical and mental behavior, we focus on the latter. We introduce a simple safe interaction model: when a human seems unaware of the robot, it should avoid going too close. In this study, people around robots are detected and tracked using sensor fusion and filtering techniques. To handle uncertainties in the dynamic environment, a Partially-Observable Markov Decision Process Model (POMDP) is used to formulate a navigation planning problem in the shared environment. People's awareness of robots is inferred and included as a state and reward model in the POMDP. The proposed planner enables a robot to change...
ArXiv, 2017
We model Human-Robot-Interaction (HRI) scenarios as linear dynamical systems and use Model Predic... more We model Human-Robot-Interaction (HRI) scenarios as linear dynamical systems and use Model Predictive Control (MPC) with mixed integer constraints to generate human-aware control policies. We motivate the approach by presenting two scenarios. The first involves an assistive robot that aims to maximize productivity while minimizing the human's workload, and the second involves a listening humanoid robot that manages its eye contact behavior to maximize "connection" and minimize social "awkwardness" with the human during the interaction. Our simulation results show that the robot generates useful behaviors as it finds control policies to minimize the specified cost function. Further, we implement the second scenario on a humanoid robot and test the eye contact scenario with 48 human participants to demonstrate and evaluate the desired controller behavior. The humanoid generated 25% more eye contact when it was told to maximize connection over when it was told t...
ArXiv, 2017
We model Human-Robot-Interaction (HRI) scenarios as linear dynamical systems and use Model Predic... more We model Human-Robot-Interaction (HRI) scenarios as linear dynamical systems and use Model Predictive Control (MPC) with mixed integer constraints to generate human-aware control policies. We motivate the approach by presenting two scenarios. The first involves an assistive robot that aims to maximize productivity while minimizing the human's workload, and the second involves a listening humanoid robot that manages its eye contact behavior to maximize "connection" and minimize social "awkwardness" with the human during the interaction. Our simulation results show that the robot generates useful behaviors as it finds control policies to minimize the specified cost function. Further, we implement the second scenario on a humanoid robot and test the eye contact scenario with 48 human participants to demonstrate and evaluate the desired controller behavior. The humanoid generated 25% more eye contact when it was told to maximize connection over when it was told t...
ArXiv, 2018
Existing gaze controllers for head-eye robots can only handle single fixation points. Here, a gen... more Existing gaze controllers for head-eye robots can only handle single fixation points. Here, a generic controller for head-eye robots capable of executing simultaneous and prioritized fixation trajectories in Cartesian space is presented. This enables the specification of multiple operational-space behaviors with priority such that the execution of a low priority head orientation task does not disturb the satisfaction of a higher prioritized eye gaze task. Through our approach, the head-eye robot inherently gains the biomimetic vestibulo-ocular reflex (VOR), which is the ability of gaze stabilization under self generated movements. The described controller utilizes recursive null space projections to encode joint limit constraints and task priorities. To handle the solution discontinuity that occurs when joint limit tasks are inserted or removed as a constraint, the Intermediate Desired Value (IDV) approach is applied. Experimental validation of the controller's properties is dem...
ArXiv, 2018
Existing gaze controllers for head-eye robots can only handle single fixation points. Here, a gen... more Existing gaze controllers for head-eye robots can only handle single fixation points. Here, a generic controller for head-eye robots capable of executing simultaneous and prioritized fixation trajectories in Cartesian space is presented. This enables the specification of multiple operational-space behaviors with priority such that the execution of a low priority head orientation task does not disturb the satisfaction of a higher prioritized eye gaze task. Through our approach, the head-eye robot inherently gains the biomimetic vestibulo-ocular reflex (VOR), which is the ability of gaze stabilization under self generated movements. The described controller utilizes recursive null space projections to encode joint limit constraints and task priorities. To handle the solution discontinuity that occurs when joint limit tasks are inserted or removed as a constraint, the Intermediate Desired Value (IDV) approach is applied. Experimental validation of the controller's properties is dem...
While the area of whole-body controllers for humanoids have matured in recent years, deploying hu... more While the area of whole-body controllers for humanoids have matured in recent years, deploying humanoid robots in human environments remains a challenge. One difficulty comes from the discrepancy between the models used to design the controllers and the unmodeled phenomena of the real world. Therefore, deploying robots require practical solutions that are robust to these discrepancies. To this end, this dissertation tackles a subset of real-world deployment problems and offers practical solutions to the domains explored. A common theme in the solutions presented have been to reformulate whole-body control concepts to make them realizable in the real-world. In particular, the use of kinematics for task-space trajectory generation in the high-level and joint position and velocity feedback control in the low-level play an important role in functional deployment. The former finds practical use, for instance, in gaze generation, thermal recovery operations, and whole-body manipulation, while the latter is important in dynamic balancing of biped robots and overall trajectory stabilization. This is not to claim that robot dynamics should be ignored for practical deployment. Instead however, the appropriate use of kinematics and dynamics information is the critical factor in efficient trajectory generation and robust feedback control of humanoids. To give evidence to this claim, the discussed approaches have been successfully deployed on a variety of humanoid platforms.
While the area of whole-body controllers for humanoids have matured in recent years, deploying hu... more While the area of whole-body controllers for humanoids have matured in recent years, deploying humanoid robots in human environments remains a challenge. One difficulty comes from the discrepancy between the models used to design the controllers and the unmodeled phenomena of the real world. Therefore, deploying robots require practical solutions that are robust to these discrepancies. To this end, this dissertation tackles a subset of real-world deployment problems and offers practical solutions to the domains explored. A common theme in the solutions presented have been to reformulate whole-body control concepts to make them realizable in the real-world. In particular, the use of kinematics for task-space trajectory generation in the high-level and joint position and velocity feedback control in the low-level play an important role in functional deployment. The former finds practical use, for instance, in gaze generation, thermal recovery operations, and whole-body manipulation, while the latter is important in dynamic balancing of biped robots and overall trajectory stabilization. This is not to claim that robot dynamics should be ignored for practical deployment. Instead however, the appropriate use of kinematics and dynamics information is the critical factor in efficient trajectory generation and robust feedback control of humanoids. To give evidence to this claim, the discussed approaches have been successfully deployed on a variety of humanoid platforms.
The analysis of the processing time shows satisfactory results, since this time is less than the ... more The analysis of the processing time shows satisfactory results, since this time is less than the minimun required for a robot to do a task involving human-robot interaction. The most relevant limitation in the use of the implemented software is due to fact that the package for 3d detections cannot deal with occlusions. Also, We have made a user guide of the ROS packages implemented, to facilitate their use.
The analysis of the processing time shows satisfactory results, since this time is less than the ... more The analysis of the processing time shows satisfactory results, since this time is less than the minimun required for a robot to do a task involving human-robot interaction. The most relevant limitation in the use of the implemented software is due to fact that the package for 3d detections cannot deal with occlusions. Also, We have made a user guide of the ROS packages implemented, to facilitate their use.
2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids), 2019
As part of a feasibility study, this paper shows the NASA Valkyrie humanoid robot performing an e... more As part of a feasibility study, this paper shows the NASA Valkyrie humanoid robot performing an endto-end improvised explosive device (IED) response task. To demonstrate and evaluate robot capabilities, sub-tasks highlight different locomotion, manipulation, and perception requirements: traversing uneven terrain, passing through a narrow passageway, opening a car door, retrieving a suspected IED, and securing the IED in a total containment vessel (TCV). For each sub-task, a description of the technical approach and the hidden challenges that were overcome during development are presented. The discussion of results, which explicitly includes existing limitations, is aimed at motivating continued research and development to enable practical deployment of humanoid robots for IED response. For instance, the data shows that operator pauses contribute to 50% of the total completion time, which implies that further work is needed on user interfaces for increasing task completion efficiency.
2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids), 2019
As part of a feasibility study, this paper shows the NASA Valkyrie humanoid robot performing an e... more As part of a feasibility study, this paper shows the NASA Valkyrie humanoid robot performing an endto-end improvised explosive device (IED) response task. To demonstrate and evaluate robot capabilities, sub-tasks highlight different locomotion, manipulation, and perception requirements: traversing uneven terrain, passing through a narrow passageway, opening a car door, retrieving a suspected IED, and securing the IED in a total containment vessel (TCV). For each sub-task, a description of the technical approach and the hidden challenges that were overcome during development are presented. The discussion of results, which explicitly includes existing limitations, is aimed at motivating continued research and development to enable practical deployment of humanoid robots for IED response. For instance, the data shows that operator pauses contribute to 50% of the total completion time, which implies that further work is needed on user interfaces for increasing task completion efficiency.
2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids), 2016
Exploiting full-body dynamics in feedback control can enhance the balancing capability of a legge... more Exploiting full-body dynamics in feedback control can enhance the balancing capability of a legged system using various techniques such as Whole-Body Control (WBC) or Centroidal Momentum control. However, motion control of the NAO robot based on full-body dynamics has not been extensively studied due to its limited computation power, limited sensors, and restricted access to its low-level controllers. Whole-Body Operational Space Control (WBOSC) is a promising WBC approach for NAO, since its closed form solution provides computational efficiency. But, users need to provide the velocity map (Jacobian) between operational space and configuration space to add the balancing control task. Thus, in this paper, we formulate the Jacobians incorporating the Capture Point (CP) technique [1] and the Centroidal Angular Momentum (CAM) [2], [3], and demonstrate the enhancement of balancing capability in a physics-based simulation. While WBOSC reduces the computational load, implementing WBC in the real system with limited sensing capability and built-in joint position control is challenging. We show that the combination of a virtual model as an interface to the real robot and an Extended Kalman-filter based orientation estimator results in a stable implementation of a closed-loop WBOSC. We demonstrate the validity of our approach by performing a dynamic kicking motion on the physical NAO robot. Overall, the contributions of this paper are: (1) to extend WBOSC by adding CAM and CP control tasks, and (2) to implement WBOSC in a restricted physical system by utilizing a virtual model and an orientation estimator.
The International Journal of Robotics Research, 2020
Whole-body control (WBC) is a generic task-oriented control method for feedback control of loco-m... more Whole-body control (WBC) is a generic task-oriented control method for feedback control of loco-manipulation behaviors in humanoid robots. The combination of WBC and model-based walking controllers has been widely utilized in various humanoid robots. However, to date, the WBC method has not been employed for unsupported passive-ankle dynamic locomotion. As such, in this article, we devise a new WBC, dubbed the whole-body locomotion controller (WBLC), that can achieve experimental dynamic walking on unsupported passive-ankle biped robots. A key aspect of WBLC is the relaxation of contact constraints such that the control commands produce reduced jerk when switching foot contacts. To achieve robust dynamic locomotion, we conduct an in-depth analysis of uncertainty for our dynamic walking algorithm called the time-to-velocity-reversal (TVR) planner. The uncertainty study is fundamental as it allows us to improve the control algorithms and mechanical structure of our robot to fulfill th...
2020 IEEE International Conference on Robotics and Automation (ICRA), 2020
We present a method that finds locomanipulation plans that perform simultaneous locomotion and ma... more We present a method that finds locomanipulation plans that perform simultaneous locomotion and manipulation of objects for a desired end-effector trajectory. Key to our approach is to consider a generic locomotion constraint manifold that defines the locomotion scheme of the robot and then using this constraint manifold to search for admissible manipulation trajectories. The problem is formulated as a weighted-A* graph search whose planner output is a sequence of contact transitions and a path progression trajectory to construct the whole-body kinodynamic locomanipulation plan. We also provide a method for computing, visualizing and learning the locomanipulability region, which is used to efficiently evaluate the edge transition feasibility during the graph search. Experiments are performed on the NASA Valkyrie robot platform that utilizes a dynamic locomotion approach, called the divergent-component-of-motion (DCM), on two example locomanipulation scenarios.
2020 IEEE International Conference on Robotics and Automation (ICRA), 2020
We present a method that finds locomanipulation plans that perform simultaneous locomotion and ma... more We present a method that finds locomanipulation plans that perform simultaneous locomotion and manipulation of objects for a desired end-effector trajectory. Key to our approach is to consider a generic locomotion constraint manifold that defines the locomotion scheme of the robot and then using this constraint manifold to search for admissible manipulation trajectories. The problem is formulated as a weighted-A* graph search whose planner output is a sequence of contact transitions and a path progression trajectory to construct the whole-body kinodynamic locomanipulation plan. We also provide a method for computing, visualizing and learning the locomanipulability region, which is used to efficiently evaluate the edge transition feasibility during the graph search. Experiments are performed on the NASA Valkyrie robot platform that utilizes a dynamic locomotion approach, called the divergent-component-of-motion (DCM), on two example locomanipulation scenarios.
2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids), 2018
We propose a methodology for dynamically balancing passive-ankled bipeds and full humanoids. As d... more We propose a methodology for dynamically balancing passive-ankled bipeds and full humanoids. As dynamic locomotion without ankle-actuation is more difficult than with actuated feet, our control scheme adopts an efficient wholebody controller that combines inverse kinematics, contactconsistent feed-forward torques, and low-level motor position controllers. To understand real-world sensing and controller requirements, we perform an uncertainty analysis on the linearinverted-pendulum (LIP)-based footstep planner. This enables us to identify necessary hardware and control refinements to demonstrate that our controller can achieve long-term unsupported dynamic balancing on our series-elastic biped, Mercury. Through simulations, we also demonstrate that our control scheme for dynamic balancing with passive-ankles is applicable to full humanoid robots.
2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids), 2018
We propose a methodology for dynamically balancing passive-ankled bipeds and full humanoids. As d... more We propose a methodology for dynamically balancing passive-ankled bipeds and full humanoids. As dynamic locomotion without ankle-actuation is more difficult than with actuated feet, our control scheme adopts an efficient wholebody controller that combines inverse kinematics, contactconsistent feed-forward torques, and low-level motor position controllers. To understand real-world sensing and controller requirements, we perform an uncertainty analysis on the linearinverted-pendulum (LIP)-based footstep planner. This enables us to identify necessary hardware and control refinements to demonstrate that our controller can achieve long-term unsupported dynamic balancing on our series-elastic biped, Mercury. Through simulations, we also demonstrate that our control scheme for dynamic balancing with passive-ankles is applicable to full humanoid robots.
ArXiv, 2018
When mobile robots maneuver near people, they run the risk of rudely blocking their paths; but no... more When mobile robots maneuver near people, they run the risk of rudely blocking their paths; but not all people behave the same around robots. People that have not noticed the robot are the most difficult to predict. This paper investigates how mobile robots can generate acceptable paths in dynamic environments by predicting human behavior. Here, human behavior may include both physical and mental behavior, we focus on the latter. We introduce a simple safe interaction model: when a human seems unaware of the robot, it should avoid going too close. In this study, people around robots are detected and tracked using sensor fusion and filtering techniques. To handle uncertainties in the dynamic environment, a Partially-Observable Markov Decision Process Model (POMDP) is used to formulate a navigation planning problem in the shared environment. People's awareness of robots is inferred and included as a state and reward model in the POMDP. The proposed planner enables a robot to change...
ArXiv, 2018
When mobile robots maneuver near people, they run the risk of rudely blocking their paths; but no... more When mobile robots maneuver near people, they run the risk of rudely blocking their paths; but not all people behave the same around robots. People that have not noticed the robot are the most difficult to predict. This paper investigates how mobile robots can generate acceptable paths in dynamic environments by predicting human behavior. Here, human behavior may include both physical and mental behavior, we focus on the latter. We introduce a simple safe interaction model: when a human seems unaware of the robot, it should avoid going too close. In this study, people around robots are detected and tracked using sensor fusion and filtering techniques. To handle uncertainties in the dynamic environment, a Partially-Observable Markov Decision Process Model (POMDP) is used to formulate a navigation planning problem in the shared environment. People's awareness of robots is inferred and included as a state and reward model in the POMDP. The proposed planner enables a robot to change...
ArXiv, 2017
We model Human-Robot-Interaction (HRI) scenarios as linear dynamical systems and use Model Predic... more We model Human-Robot-Interaction (HRI) scenarios as linear dynamical systems and use Model Predictive Control (MPC) with mixed integer constraints to generate human-aware control policies. We motivate the approach by presenting two scenarios. The first involves an assistive robot that aims to maximize productivity while minimizing the human's workload, and the second involves a listening humanoid robot that manages its eye contact behavior to maximize "connection" and minimize social "awkwardness" with the human during the interaction. Our simulation results show that the robot generates useful behaviors as it finds control policies to minimize the specified cost function. Further, we implement the second scenario on a humanoid robot and test the eye contact scenario with 48 human participants to demonstrate and evaluate the desired controller behavior. The humanoid generated 25% more eye contact when it was told to maximize connection over when it was told t...
ArXiv, 2017
We model Human-Robot-Interaction (HRI) scenarios as linear dynamical systems and use Model Predic... more We model Human-Robot-Interaction (HRI) scenarios as linear dynamical systems and use Model Predictive Control (MPC) with mixed integer constraints to generate human-aware control policies. We motivate the approach by presenting two scenarios. The first involves an assistive robot that aims to maximize productivity while minimizing the human's workload, and the second involves a listening humanoid robot that manages its eye contact behavior to maximize "connection" and minimize social "awkwardness" with the human during the interaction. Our simulation results show that the robot generates useful behaviors as it finds control policies to minimize the specified cost function. Further, we implement the second scenario on a humanoid robot and test the eye contact scenario with 48 human participants to demonstrate and evaluate the desired controller behavior. The humanoid generated 25% more eye contact when it was told to maximize connection over when it was told t...
ArXiv, 2018
Existing gaze controllers for head-eye robots can only handle single fixation points. Here, a gen... more Existing gaze controllers for head-eye robots can only handle single fixation points. Here, a generic controller for head-eye robots capable of executing simultaneous and prioritized fixation trajectories in Cartesian space is presented. This enables the specification of multiple operational-space behaviors with priority such that the execution of a low priority head orientation task does not disturb the satisfaction of a higher prioritized eye gaze task. Through our approach, the head-eye robot inherently gains the biomimetic vestibulo-ocular reflex (VOR), which is the ability of gaze stabilization under self generated movements. The described controller utilizes recursive null space projections to encode joint limit constraints and task priorities. To handle the solution discontinuity that occurs when joint limit tasks are inserted or removed as a constraint, the Intermediate Desired Value (IDV) approach is applied. Experimental validation of the controller's properties is dem...
ArXiv, 2018
Existing gaze controllers for head-eye robots can only handle single fixation points. Here, a gen... more Existing gaze controllers for head-eye robots can only handle single fixation points. Here, a generic controller for head-eye robots capable of executing simultaneous and prioritized fixation trajectories in Cartesian space is presented. This enables the specification of multiple operational-space behaviors with priority such that the execution of a low priority head orientation task does not disturb the satisfaction of a higher prioritized eye gaze task. Through our approach, the head-eye robot inherently gains the biomimetic vestibulo-ocular reflex (VOR), which is the ability of gaze stabilization under self generated movements. The described controller utilizes recursive null space projections to encode joint limit constraints and task priorities. To handle the solution discontinuity that occurs when joint limit tasks are inserted or removed as a constraint, the Intermediate Desired Value (IDV) approach is applied. Experimental validation of the controller's properties is dem...
While the area of whole-body controllers for humanoids have matured in recent years, deploying hu... more While the area of whole-body controllers for humanoids have matured in recent years, deploying humanoid robots in human environments remains a challenge. One difficulty comes from the discrepancy between the models used to design the controllers and the unmodeled phenomena of the real world. Therefore, deploying robots require practical solutions that are robust to these discrepancies. To this end, this dissertation tackles a subset of real-world deployment problems and offers practical solutions to the domains explored. A common theme in the solutions presented have been to reformulate whole-body control concepts to make them realizable in the real-world. In particular, the use of kinematics for task-space trajectory generation in the high-level and joint position and velocity feedback control in the low-level play an important role in functional deployment. The former finds practical use, for instance, in gaze generation, thermal recovery operations, and whole-body manipulation, while the latter is important in dynamic balancing of biped robots and overall trajectory stabilization. This is not to claim that robot dynamics should be ignored for practical deployment. Instead however, the appropriate use of kinematics and dynamics information is the critical factor in efficient trajectory generation and robust feedback control of humanoids. To give evidence to this claim, the discussed approaches have been successfully deployed on a variety of humanoid platforms.
While the area of whole-body controllers for humanoids have matured in recent years, deploying hu... more While the area of whole-body controllers for humanoids have matured in recent years, deploying humanoid robots in human environments remains a challenge. One difficulty comes from the discrepancy between the models used to design the controllers and the unmodeled phenomena of the real world. Therefore, deploying robots require practical solutions that are robust to these discrepancies. To this end, this dissertation tackles a subset of real-world deployment problems and offers practical solutions to the domains explored. A common theme in the solutions presented have been to reformulate whole-body control concepts to make them realizable in the real-world. In particular, the use of kinematics for task-space trajectory generation in the high-level and joint position and velocity feedback control in the low-level play an important role in functional deployment. The former finds practical use, for instance, in gaze generation, thermal recovery operations, and whole-body manipulation, while the latter is important in dynamic balancing of biped robots and overall trajectory stabilization. This is not to claim that robot dynamics should be ignored for practical deployment. Instead however, the appropriate use of kinematics and dynamics information is the critical factor in efficient trajectory generation and robust feedback control of humanoids. To give evidence to this claim, the discussed approaches have been successfully deployed on a variety of humanoid platforms.
The analysis of the processing time shows satisfactory results, since this time is less than the ... more The analysis of the processing time shows satisfactory results, since this time is less than the minimun required for a robot to do a task involving human-robot interaction. The most relevant limitation in the use of the implemented software is due to fact that the package for 3d detections cannot deal with occlusions. Also, We have made a user guide of the ROS packages implemented, to facilitate their use.
The analysis of the processing time shows satisfactory results, since this time is less than the ... more The analysis of the processing time shows satisfactory results, since this time is less than the minimun required for a robot to do a task involving human-robot interaction. The most relevant limitation in the use of the implemented software is due to fact that the package for 3d detections cannot deal with occlusions. Also, We have made a user guide of the ROS packages implemented, to facilitate their use.
2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids), 2019
As part of a feasibility study, this paper shows the NASA Valkyrie humanoid robot performing an e... more As part of a feasibility study, this paper shows the NASA Valkyrie humanoid robot performing an endto-end improvised explosive device (IED) response task. To demonstrate and evaluate robot capabilities, sub-tasks highlight different locomotion, manipulation, and perception requirements: traversing uneven terrain, passing through a narrow passageway, opening a car door, retrieving a suspected IED, and securing the IED in a total containment vessel (TCV). For each sub-task, a description of the technical approach and the hidden challenges that were overcome during development are presented. The discussion of results, which explicitly includes existing limitations, is aimed at motivating continued research and development to enable practical deployment of humanoid robots for IED response. For instance, the data shows that operator pauses contribute to 50% of the total completion time, which implies that further work is needed on user interfaces for increasing task completion efficiency.
2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids), 2019
As part of a feasibility study, this paper shows the NASA Valkyrie humanoid robot performing an e... more As part of a feasibility study, this paper shows the NASA Valkyrie humanoid robot performing an endto-end improvised explosive device (IED) response task. To demonstrate and evaluate robot capabilities, sub-tasks highlight different locomotion, manipulation, and perception requirements: traversing uneven terrain, passing through a narrow passageway, opening a car door, retrieving a suspected IED, and securing the IED in a total containment vessel (TCV). For each sub-task, a description of the technical approach and the hidden challenges that were overcome during development are presented. The discussion of results, which explicitly includes existing limitations, is aimed at motivating continued research and development to enable practical deployment of humanoid robots for IED response. For instance, the data shows that operator pauses contribute to 50% of the total completion time, which implies that further work is needed on user interfaces for increasing task completion efficiency.
2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids), 2016
Exploiting full-body dynamics in feedback control can enhance the balancing capability of a legge... more Exploiting full-body dynamics in feedback control can enhance the balancing capability of a legged system using various techniques such as Whole-Body Control (WBC) or Centroidal Momentum control. However, motion control of the NAO robot based on full-body dynamics has not been extensively studied due to its limited computation power, limited sensors, and restricted access to its low-level controllers. Whole-Body Operational Space Control (WBOSC) is a promising WBC approach for NAO, since its closed form solution provides computational efficiency. But, users need to provide the velocity map (Jacobian) between operational space and configuration space to add the balancing control task. Thus, in this paper, we formulate the Jacobians incorporating the Capture Point (CP) technique [1] and the Centroidal Angular Momentum (CAM) [2], [3], and demonstrate the enhancement of balancing capability in a physics-based simulation. While WBOSC reduces the computational load, implementing WBC in the real system with limited sensing capability and built-in joint position control is challenging. We show that the combination of a virtual model as an interface to the real robot and an Extended Kalman-filter based orientation estimator results in a stable implementation of a closed-loop WBOSC. We demonstrate the validity of our approach by performing a dynamic kicking motion on the physical NAO robot. Overall, the contributions of this paper are: (1) to extend WBOSC by adding CAM and CP control tasks, and (2) to implement WBOSC in a restricted physical system by utilizing a virtual model and an orientation estimator.
The International Journal of Robotics Research, 2020
Whole-body control (WBC) is a generic task-oriented control method for feedback control of loco-m... more Whole-body control (WBC) is a generic task-oriented control method for feedback control of loco-manipulation behaviors in humanoid robots. The combination of WBC and model-based walking controllers has been widely utilized in various humanoid robots. However, to date, the WBC method has not been employed for unsupported passive-ankle dynamic locomotion. As such, in this article, we devise a new WBC, dubbed the whole-body locomotion controller (WBLC), that can achieve experimental dynamic walking on unsupported passive-ankle biped robots. A key aspect of WBLC is the relaxation of contact constraints such that the control commands produce reduced jerk when switching foot contacts. To achieve robust dynamic locomotion, we conduct an in-depth analysis of uncertainty for our dynamic walking algorithm called the time-to-velocity-reversal (TVR) planner. The uncertainty study is fundamental as it allows us to improve the control algorithms and mechanical structure of our robot to fulfill th...