Dirk Wollherr - Profile on Academia.edu (original) (raw)
Papers by Dirk Wollherr
Dynamic Window Approach for omni-directional robots with polygonal shape
Towards a dialog strategy for handling miscommunication in human-robot dialog
Robot basketball: A comparison of ball dribbling with visual and force/torque feedback
Information-Based Gaze Direction Planning Algorithm for SLAM
IEEE Transactions on Vehicular Technology, Apr 1, 2016
Knowing the course of the road together with the corresponding road boundaries is an essential co... more Knowing the course of the road together with the corresponding road boundaries is an essential component of many advanced driver assistance systems and of autonomous vehicles. This work presents an indirect, grid-based approach for road course estimation. Due to the grid representation, it is independent of specific features or particular sensors and is able to handle continuous as well as sparse road boundaries of arbitrary shape. Furthermore, the number of road courses in the scene is determined to detect road junctions and forks in the road, and the boundaries of each road course are estimated individually. The approach is based on local path planning and path clustering to find the principal moving directions through the environment. They separate the boundaries and are used for their extraction. The set of local paths and principal moving directions is reduced with approximate knowledge of the road velocity paired with system constraints, and validation and tracking assure the required robustness. Experimental results from autonomous navigation of a vehicle through an unmapped road construction site as well as quantitative evaluations demonstrate the performance of the method.
Robot Basketball: Ball Dribbling — A Modified Juggling Task
Springer eBooks, 2009
ABSTRACT Ball dribbling is a central element of basketball. One main challenge for realizing bask... more ABSTRACT Ball dribbling is a central element of basketball. One main challenge for realizing basketball robots is to achieve the stability of the periodic dribbling task. We show that the dribbling problem is closely related to robot juggling problems that are well-studied. To this end, the paper introduces a hybrid (discretecontinuous) dynamical model for ball dribbling that provides the basis for the design of reference trajectories and controllers. Furthermore the paper discusses local stability and parameter sensitivity in particular in comparison to juggling. Theoretical results are experimentally validated for ball dribbling using an industrial robot. Force/torque-based tracking and vision-based tracking are compared. For both tracking approaches, dribbling for multiple cycles is achieved. The visionbased approach performs better as compared to the force/torque-based approach, in particular for imprecise estimates of the coefficient of restitution.
IEEE Transactions on Control Systems and Technology, Nov 1, 2020
In this paper, a novel integral sliding mode observer is proposed to estimate the external distur... more In this paper, a novel integral sliding mode observer is proposed to estimate the external disturbance and velocity of Euler-Lagrangian systems. This method provides high bandwidth and precise estimation with only commanded input and position measurement. A system velocity measurement is not required to construct the sliding mode manifold. The convergence of the estimation error to zero is theoretically in finite time, which is proved by a direct Lyapunov method utilizing the passivity property of Euler-Lagrangian systems. An integral sliding manifold is designed to reduce the reaching phase, such that the robustness of the estimation is enhanced. The method has been applied to a robot manipulator to estimate the joint velocity and external contact forces in a physical human-robot task. Simulations and experiments reveal that this novel method provides fast, precise and robust estimation results and can be used to replace the measurement of an external force sensor. The successful application of this observer to a force-sensorless admittance controller for a manipulator contributes to the implementation of a sensor-free safety framework for humanrobot collaboration.
Please take over! An analysis and strategy for a driver take over request during autonomous driving
During autonomous driving, in particular conditional or highly automated driving, a critical part... more During autonomous driving, in particular conditional or highly automated driving, a critical part of the system is the driver take over request. Little focus has been given to this important aspect in an automated driving journey. A driver take over request, or TOR, can happen for various reasons and under varying circumstances. Once a TOR occurs, as defined in conditional or highly automated driving, the driver has a finite amount of time in order to take over manual control of the vehicle before the automated driving system deactivates. This paper presents a detailed analysis of why a TOR can occur, how the automated driving system should react during the TOR phase and what should happen at the end of a TOR in order to realize a safe and comfortable TOR for the driver. Various driving strategies during a TOR are presented and evaluated for a single-lane highway scenario.
IEEE Transactions on Automation Science and Engineering, 2021
proposed collision identification scheme in this paper especially focuses on overcoming the follo... more proposed collision identification scheme in this paper especially focuses on overcoming the following two challenges in practice: firstly, to timely and accurately report a collision within its early stage; secondly, to ensure a high identification accuracy in a complicated environment, where ubiquitous disturbance and noise are unneglectable. The experimental validation at the end of this paper confirms its promising application value in humanrobot collaboration.
Please take over! An analysis and strategy for a driver take over request during autonomous driving
2015 IEEE Intelligent Vehicles Symposium (IV), 2015
During autonomous driving, in particular conditional or highly automated driving, a critical part... more During autonomous driving, in particular conditional or highly automated driving, a critical part of the system is the driver take over request. Little focus has been given to this important aspect in an automated driving journey. A driver take over request, or TOR, can happen for various reasons and under varying circumstances. Once a TOR occurs, as defined in conditional or highly automated driving, the driver has a finite amount of time in order to take over manual control of the vehicle before the automated driving system deactivates. This paper presents a detailed analysis of why a TOR can occur, how the automated driving system should react during the TOR phase and what should happen at the end of a TOR in order to realize a safe and comfortable TOR for the driver. Various driving strategies during a TOR are presented and evaluated for a single-lane highway scenario.
The Autonomous City Explorer project
Legible action selection in human-robot collaboration
2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), 2017
Humans are error-prone in the presence of multiple similar tasks. While Human-Robot Collaboration... more Humans are error-prone in the presence of multiple similar tasks. While Human-Robot Collaboration (HRC) brings the advantage of combining the superiority of both humans and robots in their respective talents, it also requires the robot to communicate the task goal clearly to the human collaborator. We formalize such problems in interactive assembly tasks with hidden goal Markov decision processes (HGMDPs) to enable the symbiosis of human intention recognition and robot intention expression. In order to avoid the prohibitive computational requirements, we provide a myopic heuristic along with a feature-based state abstraction method for assembly tasks to approximate the solution of the resulting HGMDP. A user study with human subjects in round-based LEGO assembly tasks shows that our algorithm improves HRC and helps the human collaborators when the task goal is unclear to them.
IEEE Transactions on Vehicular Technology, 2016
Knowing the course of the road together with the corresponding road boundaries is an essential co... more Knowing the course of the road together with the corresponding road boundaries is an essential component of many advanced driver assistance systems and of autonomous vehicles. This work presents an indirect, grid-based approach for road course estimation. Due to the grid representation, it is independent of specific features or particular sensors and is able to handle continuous as well as sparse road boundaries of arbitrary shape. Furthermore, the number of road courses in the scene is determined to detect road junctions and forks in the road, and the boundaries of each road course are estimated individually. The approach is based on local path planning and path clustering to find the principal moving directions through the environment. They separate the boundaries and are used for their extraction. The set of local paths and principal moving directions is reduced with approximate knowledge of the road velocity paired with system constraints, and validation and tracking assure the required robustness. Experimental results from autonomous navigation of a vehicle through an unmapped road construction site as well as quantitative evaluations demonstrate the performance of the method.
IEEE Transactions on Intelligent Transportation Systems, 2019
Object tracking is crucial for planning safe maneuvers of mobile robots in dynamic environments, ... more Object tracking is crucial for planning safe maneuvers of mobile robots in dynamic environments, in particular for autonomous driving with surrounding traffic participants. Multistage processing of sensor measurement data is thereby required to obtain abstracted high-level objects, such as vehicles. This also includes sensor fusion, data association, and temporal filtering. Often, an early-stage object abstraction is performed, which, however, is critical, as it results in information loss regarding the subsequent processing steps. We present a new grid-based object tracking approach that, in contrast, is based on already fused measurement data. The input is thereby pre-processed, without abstracting objects, by the spatial grid cell discretization of a dynamic occupancy grid, which enables a generic multi-sensor detection of moving objects. On the basis of already associated occupied cells, presented in our previous work, this paper investigates the subsequent object state estimation. The object pose and shape estimation thereby benefit from the freespace information contained in the input grid, which is evaluated to determine the current visibility of extracted object parts. An integrated object classification concept further enhances the assumed object size. For a precise dynamic motion state estimation, radar Doppler velocity measurements are integrated into the input data and processed directly on the object-level. Our approach is evaluated with real sensor data in the context of autonomous driving in challenging urban scenarios.
International Journal of Social Robotics, 2016
The inclusion of social and human-like behaviors is recently emphasized within mobile robot locom... more The inclusion of social and human-like behaviors is recently emphasized within mobile robot locomotion. These behaviors are required to support the seamless integration of mobile robots into environments which they share with humans. This work demonstrates a distinct benefit of these behaviors, which goes beyond positive apperception. It is shown that human-like robot locomotion reduces the planning effort for all agents within an environment. This effect is revealed in an experiment that compares human locomotion during avoidance of an oncoming human or wheeled robot. In order to evaluate recorded data, a framework for the analysis of human trajectories is proposed. Confidence intervals based on a spline regression model are used to account for variance in the data. This qualitative method is complemented by a comparative analysis, that quantifies differences and analogies within the data. Thus, the framework allows for a statistically feasible qualitative and quantitative analysis of trajectories. Results show, that extra planning effort for the avoidance is prevented by readable human-like robot locomotion. The study indicates that locomotion planning requires less effort from subjects if the mutual trajectory prediction is facilitated by robots that externalize intentions and comply with human-like behaviors.
Next generation of industrial revolution will be featured with broad applications of intelligent ... more Next generation of industrial revolution will be featured with broad applications of intelligent technologies; among those popular ones are intelligent manufacturing and autonomous products like vehicles and robotic systems. In both cases, autonomous operations are at the center of the stage, in which appropriate sensing and perception play critical roles. Indeed, recent advances in sensing and perception technologies have produced exciting new ideas in facilitating autonomous manufacturing and/or robotic vehicular systems. These technologies will potentially evolve with more and more ‘smart functions’ and move manufacturing and robotic systems from single structured operation to sensing/perception-based self-governed yet collaborative multisystem operations. This Focused Section is dedicated to new progresses in modeling, design, control, communication, and implementation of sensing and perception systems for autonomous and/or networked robotics, and intends to provide the state-of...
International Journal of Intelligent Robotics and Applications, 2017
This paper presents a method to localize a robot in a global coordinate frame based on a sparse 2... more This paper presents a method to localize a robot in a global coordinate frame based on a sparse 2D map containing outlines of building and road network information and no location prior information. Its input is a single 3D laser scan of the surroundings of the robot. The approach extends the generic chamfer matching template matching technique from image processing by including visibility analysis in the cost function. Thus, the observed building planes are matched to the expected view of the corresponding map section instead of to the entire map, which makes a more accurate matching possible. Since this formulation operates on generic edge maps from visual sensors, the matching formulation can be expected to generalize to other input data, e.g., from monocular or stereo cameras. The method is evaluated on two large datasets collected in different real-world urban settings and compared to a baseline method from literature and to the standard chamfer matching approach, where it shows considerable performance benefits, as well as the feasibility of global localization based on sparse building outline data.
2015 IEEE International Workshop on Advanced Robotics and its Social Impacts (ARSO), 2015
Providing robots with the ability to move humanlike is one of the recent challenges for researche... more Providing robots with the ability to move humanlike is one of the recent challenges for researchers who work on motion planning in human populated environments. Humanlike motions help a human interaction partner to intuitively grasp the intention of the robot. However, the problem of validating the degree of human-likeness of a robot motion is rarely addressed, especially for the forward motion during navigation. One approach is using similarity measures to compare the robot trajectories directly with human ones. For this reason, this paper investigates different methods from the time series analysis that can be applied to measure the similarity between trajectories: the average Euclidean distance, the Dynamic Time Warping distance, and the Longest Common Subsequence. We aim to identify the measure that performs the same way as a human who rates the similarity. Thus, the evaluation of the methods is based on a questionnaire that examines the human perception of differences between walking motions. It is concluded that the human similarity perception is reproduced best by using the Dynamic Time Warping and comparing the derivatives of the path and velocity profiles instead of the absolute values.
An approach to integrate human motion prediction into local obstacle avoidance in close human-robot collaboration
2015 IEEE International Workshop on Advanced Robotics and its Social Impacts (ARSO), 2015
Within Human-Robot Collaboration (HRC) safety is one key-issue that has to be guaranteed at any t... more Within Human-Robot Collaboration (HRC) safety is one key-issue that has to be guaranteed at any time during joint collaboration. Collisions in a shared workspace of a Human-Robot-Team (HRT) must be prevented. In addition, the comfort of the collaboration behavior should be provided. Facing these challenges, a robot has to be able to detect critical states at an early stage on the one hand and should react to them within a very short time span on the other hand. In this paper a collision avoidance algorithm using compliance control that guarantees a fast reaction to dynamic obstacles, e.g. humans, without the need of high computational effort is outlined. To further improve the avoidance behavior of the robot, a human motion prediction algorithm based on the minimum-jerk model is integrated. In an experimental analysis of a case-study about collecting LEGO-bricks on a table with various subjects, the impact of the integration of human motion prediction on both the robot's reaction time and human's perception of the robot co-worker is studied. Finally, the comfort and acceptance of the robot colleague by the human collaborator is drawn out through an analysis of the subjective human feedback questionnaires.
IURO – Soziale Mensch-Roboter-Interaktion in den Straßen von München
at - Automatisierungstechnik, 2015
ZusammenfassungDas Projekt
Dynamic Window Approach for omni-directional robots with polygonal shape
Towards a dialog strategy for handling miscommunication in human-robot dialog
Robot basketball: A comparison of ball dribbling with visual and force/torque feedback
Information-Based Gaze Direction Planning Algorithm for SLAM
IEEE Transactions on Vehicular Technology, Apr 1, 2016
Knowing the course of the road together with the corresponding road boundaries is an essential co... more Knowing the course of the road together with the corresponding road boundaries is an essential component of many advanced driver assistance systems and of autonomous vehicles. This work presents an indirect, grid-based approach for road course estimation. Due to the grid representation, it is independent of specific features or particular sensors and is able to handle continuous as well as sparse road boundaries of arbitrary shape. Furthermore, the number of road courses in the scene is determined to detect road junctions and forks in the road, and the boundaries of each road course are estimated individually. The approach is based on local path planning and path clustering to find the principal moving directions through the environment. They separate the boundaries and are used for their extraction. The set of local paths and principal moving directions is reduced with approximate knowledge of the road velocity paired with system constraints, and validation and tracking assure the required robustness. Experimental results from autonomous navigation of a vehicle through an unmapped road construction site as well as quantitative evaluations demonstrate the performance of the method.
Robot Basketball: Ball Dribbling — A Modified Juggling Task
Springer eBooks, 2009
ABSTRACT Ball dribbling is a central element of basketball. One main challenge for realizing bask... more ABSTRACT Ball dribbling is a central element of basketball. One main challenge for realizing basketball robots is to achieve the stability of the periodic dribbling task. We show that the dribbling problem is closely related to robot juggling problems that are well-studied. To this end, the paper introduces a hybrid (discretecontinuous) dynamical model for ball dribbling that provides the basis for the design of reference trajectories and controllers. Furthermore the paper discusses local stability and parameter sensitivity in particular in comparison to juggling. Theoretical results are experimentally validated for ball dribbling using an industrial robot. Force/torque-based tracking and vision-based tracking are compared. For both tracking approaches, dribbling for multiple cycles is achieved. The visionbased approach performs better as compared to the force/torque-based approach, in particular for imprecise estimates of the coefficient of restitution.
IEEE Transactions on Control Systems and Technology, Nov 1, 2020
In this paper, a novel integral sliding mode observer is proposed to estimate the external distur... more In this paper, a novel integral sliding mode observer is proposed to estimate the external disturbance and velocity of Euler-Lagrangian systems. This method provides high bandwidth and precise estimation with only commanded input and position measurement. A system velocity measurement is not required to construct the sliding mode manifold. The convergence of the estimation error to zero is theoretically in finite time, which is proved by a direct Lyapunov method utilizing the passivity property of Euler-Lagrangian systems. An integral sliding manifold is designed to reduce the reaching phase, such that the robustness of the estimation is enhanced. The method has been applied to a robot manipulator to estimate the joint velocity and external contact forces in a physical human-robot task. Simulations and experiments reveal that this novel method provides fast, precise and robust estimation results and can be used to replace the measurement of an external force sensor. The successful application of this observer to a force-sensorless admittance controller for a manipulator contributes to the implementation of a sensor-free safety framework for humanrobot collaboration.
Please take over! An analysis and strategy for a driver take over request during autonomous driving
During autonomous driving, in particular conditional or highly automated driving, a critical part... more During autonomous driving, in particular conditional or highly automated driving, a critical part of the system is the driver take over request. Little focus has been given to this important aspect in an automated driving journey. A driver take over request, or TOR, can happen for various reasons and under varying circumstances. Once a TOR occurs, as defined in conditional or highly automated driving, the driver has a finite amount of time in order to take over manual control of the vehicle before the automated driving system deactivates. This paper presents a detailed analysis of why a TOR can occur, how the automated driving system should react during the TOR phase and what should happen at the end of a TOR in order to realize a safe and comfortable TOR for the driver. Various driving strategies during a TOR are presented and evaluated for a single-lane highway scenario.
IEEE Transactions on Automation Science and Engineering, 2021
proposed collision identification scheme in this paper especially focuses on overcoming the follo... more proposed collision identification scheme in this paper especially focuses on overcoming the following two challenges in practice: firstly, to timely and accurately report a collision within its early stage; secondly, to ensure a high identification accuracy in a complicated environment, where ubiquitous disturbance and noise are unneglectable. The experimental validation at the end of this paper confirms its promising application value in humanrobot collaboration.
Please take over! An analysis and strategy for a driver take over request during autonomous driving
2015 IEEE Intelligent Vehicles Symposium (IV), 2015
During autonomous driving, in particular conditional or highly automated driving, a critical part... more During autonomous driving, in particular conditional or highly automated driving, a critical part of the system is the driver take over request. Little focus has been given to this important aspect in an automated driving journey. A driver take over request, or TOR, can happen for various reasons and under varying circumstances. Once a TOR occurs, as defined in conditional or highly automated driving, the driver has a finite amount of time in order to take over manual control of the vehicle before the automated driving system deactivates. This paper presents a detailed analysis of why a TOR can occur, how the automated driving system should react during the TOR phase and what should happen at the end of a TOR in order to realize a safe and comfortable TOR for the driver. Various driving strategies during a TOR are presented and evaluated for a single-lane highway scenario.
The Autonomous City Explorer project
Legible action selection in human-robot collaboration
2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), 2017
Humans are error-prone in the presence of multiple similar tasks. While Human-Robot Collaboration... more Humans are error-prone in the presence of multiple similar tasks. While Human-Robot Collaboration (HRC) brings the advantage of combining the superiority of both humans and robots in their respective talents, it also requires the robot to communicate the task goal clearly to the human collaborator. We formalize such problems in interactive assembly tasks with hidden goal Markov decision processes (HGMDPs) to enable the symbiosis of human intention recognition and robot intention expression. In order to avoid the prohibitive computational requirements, we provide a myopic heuristic along with a feature-based state abstraction method for assembly tasks to approximate the solution of the resulting HGMDP. A user study with human subjects in round-based LEGO assembly tasks shows that our algorithm improves HRC and helps the human collaborators when the task goal is unclear to them.
IEEE Transactions on Vehicular Technology, 2016
Knowing the course of the road together with the corresponding road boundaries is an essential co... more Knowing the course of the road together with the corresponding road boundaries is an essential component of many advanced driver assistance systems and of autonomous vehicles. This work presents an indirect, grid-based approach for road course estimation. Due to the grid representation, it is independent of specific features or particular sensors and is able to handle continuous as well as sparse road boundaries of arbitrary shape. Furthermore, the number of road courses in the scene is determined to detect road junctions and forks in the road, and the boundaries of each road course are estimated individually. The approach is based on local path planning and path clustering to find the principal moving directions through the environment. They separate the boundaries and are used for their extraction. The set of local paths and principal moving directions is reduced with approximate knowledge of the road velocity paired with system constraints, and validation and tracking assure the required robustness. Experimental results from autonomous navigation of a vehicle through an unmapped road construction site as well as quantitative evaluations demonstrate the performance of the method.
IEEE Transactions on Intelligent Transportation Systems, 2019
Object tracking is crucial for planning safe maneuvers of mobile robots in dynamic environments, ... more Object tracking is crucial for planning safe maneuvers of mobile robots in dynamic environments, in particular for autonomous driving with surrounding traffic participants. Multistage processing of sensor measurement data is thereby required to obtain abstracted high-level objects, such as vehicles. This also includes sensor fusion, data association, and temporal filtering. Often, an early-stage object abstraction is performed, which, however, is critical, as it results in information loss regarding the subsequent processing steps. We present a new grid-based object tracking approach that, in contrast, is based on already fused measurement data. The input is thereby pre-processed, without abstracting objects, by the spatial grid cell discretization of a dynamic occupancy grid, which enables a generic multi-sensor detection of moving objects. On the basis of already associated occupied cells, presented in our previous work, this paper investigates the subsequent object state estimation. The object pose and shape estimation thereby benefit from the freespace information contained in the input grid, which is evaluated to determine the current visibility of extracted object parts. An integrated object classification concept further enhances the assumed object size. For a precise dynamic motion state estimation, radar Doppler velocity measurements are integrated into the input data and processed directly on the object-level. Our approach is evaluated with real sensor data in the context of autonomous driving in challenging urban scenarios.
International Journal of Social Robotics, 2016
The inclusion of social and human-like behaviors is recently emphasized within mobile robot locom... more The inclusion of social and human-like behaviors is recently emphasized within mobile robot locomotion. These behaviors are required to support the seamless integration of mobile robots into environments which they share with humans. This work demonstrates a distinct benefit of these behaviors, which goes beyond positive apperception. It is shown that human-like robot locomotion reduces the planning effort for all agents within an environment. This effect is revealed in an experiment that compares human locomotion during avoidance of an oncoming human or wheeled robot. In order to evaluate recorded data, a framework for the analysis of human trajectories is proposed. Confidence intervals based on a spline regression model are used to account for variance in the data. This qualitative method is complemented by a comparative analysis, that quantifies differences and analogies within the data. Thus, the framework allows for a statistically feasible qualitative and quantitative analysis of trajectories. Results show, that extra planning effort for the avoidance is prevented by readable human-like robot locomotion. The study indicates that locomotion planning requires less effort from subjects if the mutual trajectory prediction is facilitated by robots that externalize intentions and comply with human-like behaviors.
Next generation of industrial revolution will be featured with broad applications of intelligent ... more Next generation of industrial revolution will be featured with broad applications of intelligent technologies; among those popular ones are intelligent manufacturing and autonomous products like vehicles and robotic systems. In both cases, autonomous operations are at the center of the stage, in which appropriate sensing and perception play critical roles. Indeed, recent advances in sensing and perception technologies have produced exciting new ideas in facilitating autonomous manufacturing and/or robotic vehicular systems. These technologies will potentially evolve with more and more ‘smart functions’ and move manufacturing and robotic systems from single structured operation to sensing/perception-based self-governed yet collaborative multisystem operations. This Focused Section is dedicated to new progresses in modeling, design, control, communication, and implementation of sensing and perception systems for autonomous and/or networked robotics, and intends to provide the state-of...
International Journal of Intelligent Robotics and Applications, 2017
This paper presents a method to localize a robot in a global coordinate frame based on a sparse 2... more This paper presents a method to localize a robot in a global coordinate frame based on a sparse 2D map containing outlines of building and road network information and no location prior information. Its input is a single 3D laser scan of the surroundings of the robot. The approach extends the generic chamfer matching template matching technique from image processing by including visibility analysis in the cost function. Thus, the observed building planes are matched to the expected view of the corresponding map section instead of to the entire map, which makes a more accurate matching possible. Since this formulation operates on generic edge maps from visual sensors, the matching formulation can be expected to generalize to other input data, e.g., from monocular or stereo cameras. The method is evaluated on two large datasets collected in different real-world urban settings and compared to a baseline method from literature and to the standard chamfer matching approach, where it shows considerable performance benefits, as well as the feasibility of global localization based on sparse building outline data.
2015 IEEE International Workshop on Advanced Robotics and its Social Impacts (ARSO), 2015
Providing robots with the ability to move humanlike is one of the recent challenges for researche... more Providing robots with the ability to move humanlike is one of the recent challenges for researchers who work on motion planning in human populated environments. Humanlike motions help a human interaction partner to intuitively grasp the intention of the robot. However, the problem of validating the degree of human-likeness of a robot motion is rarely addressed, especially for the forward motion during navigation. One approach is using similarity measures to compare the robot trajectories directly with human ones. For this reason, this paper investigates different methods from the time series analysis that can be applied to measure the similarity between trajectories: the average Euclidean distance, the Dynamic Time Warping distance, and the Longest Common Subsequence. We aim to identify the measure that performs the same way as a human who rates the similarity. Thus, the evaluation of the methods is based on a questionnaire that examines the human perception of differences between walking motions. It is concluded that the human similarity perception is reproduced best by using the Dynamic Time Warping and comparing the derivatives of the path and velocity profiles instead of the absolute values.
An approach to integrate human motion prediction into local obstacle avoidance in close human-robot collaboration
2015 IEEE International Workshop on Advanced Robotics and its Social Impacts (ARSO), 2015
Within Human-Robot Collaboration (HRC) safety is one key-issue that has to be guaranteed at any t... more Within Human-Robot Collaboration (HRC) safety is one key-issue that has to be guaranteed at any time during joint collaboration. Collisions in a shared workspace of a Human-Robot-Team (HRT) must be prevented. In addition, the comfort of the collaboration behavior should be provided. Facing these challenges, a robot has to be able to detect critical states at an early stage on the one hand and should react to them within a very short time span on the other hand. In this paper a collision avoidance algorithm using compliance control that guarantees a fast reaction to dynamic obstacles, e.g. humans, without the need of high computational effort is outlined. To further improve the avoidance behavior of the robot, a human motion prediction algorithm based on the minimum-jerk model is integrated. In an experimental analysis of a case-study about collecting LEGO-bricks on a table with various subjects, the impact of the integration of human motion prediction on both the robot's reaction time and human's perception of the robot co-worker is studied. Finally, the comfort and acceptance of the robot colleague by the human collaborator is drawn out through an analysis of the subjective human feedback questionnaires.
IURO – Soziale Mensch-Roboter-Interaktion in den Straßen von München
at - Automatisierungstechnik, 2015
ZusammenfassungDas Projekt