Daniel F Ordoñez-Apraez - Academia.edu (original) (raw)
Uploads
Papers by Daniel F Ordoñez-Apraez
2022 International Conference on Robotics and Automation (ICRA)
Fig. 1: Control policies for the biped robot Bolt (1.05[m/s]) and quadruped robot Solo (0.96[m/s]... more Fig. 1: Control policies for the biped robot Bolt (1.05[m/s]) and quadruped robot Solo (0.96[m/s]) learned with model-free RL learning guided with the spring-loaded inverted pendulum model. All gaits across training seeds feature periodicity, limbs coordination and natural spring-mass center of mass dynamics.
IEEE International Conference on Robotics and Automation (ICRA) , 2022
Learning controllers that reproduce legged locomotion in nature has been a long-time goal in robo... more Learning controllers that reproduce legged locomotion in nature has been a long-time goal in robotics and computer graphics. While yielding promising results, recent approaches are not yet flexible enough to be applicable to legged systems of different morphologies. This is partly because they often rely on precise motion capture references or elaborate learning environments that ensure the naturality of the emergent locomotion gaits but prevent generalization. This work proposes a generic approach for ensuring realism in locomotion by guiding the learning process with the spring-loaded inverted pendulum model as a reference. Leveraging on the exploration capacities of Reinforcement Learning (RL), we learn a control policy that fills in the information gap between the template model and full-body dynamics required to maintain stable and periodic locomotion. The proposed approach can be applied to robots of different sizes and morphologies and adapted to any RL technique and control architecture.
We present experimental results showing that even in a model-free setup and with a simple reactive control architecture, the learned policies can generate realistic and energy-efficient locomotion gaits for a bipedal and a quadrupedal robot. And most importantly, this is achieved without using motion capture, strong constraints in the dynamics or kinematics of the robot, nor prescribing limb coordination. We provide supplemental videos for qualitative analysis of the naturality of the learned gaits.
2022 International Conference on Robotics and Automation (ICRA)
Fig. 1: Control policies for the biped robot Bolt (1.05[m/s]) and quadruped robot Solo (0.96[m/s]... more Fig. 1: Control policies for the biped robot Bolt (1.05[m/s]) and quadruped robot Solo (0.96[m/s]) learned with model-free RL learning guided with the spring-loaded inverted pendulum model. All gaits across training seeds feature periodicity, limbs coordination and natural spring-mass center of mass dynamics.
IEEE International Conference on Robotics and Automation (ICRA) , 2022
Learning controllers that reproduce legged locomotion in nature has been a long-time goal in robo... more Learning controllers that reproduce legged locomotion in nature has been a long-time goal in robotics and computer graphics. While yielding promising results, recent approaches are not yet flexible enough to be applicable to legged systems of different morphologies. This is partly because they often rely on precise motion capture references or elaborate learning environments that ensure the naturality of the emergent locomotion gaits but prevent generalization. This work proposes a generic approach for ensuring realism in locomotion by guiding the learning process with the spring-loaded inverted pendulum model as a reference. Leveraging on the exploration capacities of Reinforcement Learning (RL), we learn a control policy that fills in the information gap between the template model and full-body dynamics required to maintain stable and periodic locomotion. The proposed approach can be applied to robots of different sizes and morphologies and adapted to any RL technique and control architecture.
We present experimental results showing that even in a model-free setup and with a simple reactive control architecture, the learned policies can generate realistic and energy-efficient locomotion gaits for a bipedal and a quadrupedal robot. And most importantly, this is achieved without using motion capture, strong constraints in the dynamics or kinematics of the robot, nor prescribing limb coordination. We provide supplemental videos for qualitative analysis of the naturality of the learned gaits.