TY - GEN
T1 - Efficient humanoid contact planning using learned centroidal dynamics prediction
AU - Lin, Yu Chi
AU - Ponton, Brahayam
AU - Righetti, Ludovic
AU - Berenson, Dmitry
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/5
Y1 - 2019/5
N2 - Humanoid robots dynamically navigate an environment by interacting with it via contact wrenches exerted at intermittent contact poses. Therefore, it is important to consider dynamics when planning a contact sequence. Traditional contact planning approaches assume a quasi-static balance criterion to reduce the computational challenges of selecting a contact sequence over a rough terrain. This however limits the applicability of the approach when dynamic motions are required, such as when walking down a steep slope or crossing a wide gap. Recent methods overcome this limitation with the help of efficient mixed integer convex programming solvers capable of synthesizing dynamic contact sequences. Nevertheless, its exponential-time complexity limits its applicability to short time horizon contact sequences within small environments. In this paper, we go beyond current approaches by learning a prediction of the dynamic evolution of the robot centroidal momenta, which can then be used for quickly generating dynamically robust contact sequences for robots with arms and legs using a search-based contact planner. We demonstrate the efficiency and quality of the results of the proposed approach in a set of dynamically challenging scenarios.
AB - Humanoid robots dynamically navigate an environment by interacting with it via contact wrenches exerted at intermittent contact poses. Therefore, it is important to consider dynamics when planning a contact sequence. Traditional contact planning approaches assume a quasi-static balance criterion to reduce the computational challenges of selecting a contact sequence over a rough terrain. This however limits the applicability of the approach when dynamic motions are required, such as when walking down a steep slope or crossing a wide gap. Recent methods overcome this limitation with the help of efficient mixed integer convex programming solvers capable of synthesizing dynamic contact sequences. Nevertheless, its exponential-time complexity limits its applicability to short time horizon contact sequences within small environments. In this paper, we go beyond current approaches by learning a prediction of the dynamic evolution of the robot centroidal momenta, which can then be used for quickly generating dynamically robust contact sequences for robots with arms and legs using a search-based contact planner. We demonstrate the efficiency and quality of the results of the proposed approach in a set of dynamically challenging scenarios.
UR - http://www.scopus.com/inward/record.url?scp=85071494131&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85071494131&partnerID=8YFLogxK
U2 - 10.1109/ICRA.2019.8794032
DO - 10.1109/ICRA.2019.8794032
M3 - Conference contribution
AN - SCOPUS:85071494131
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 5280
EP - 5286
BT - 2019 International Conference on Robotics and Automation, ICRA 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 International Conference on Robotics and Automation, ICRA 2019
Y2 - 20 May 2019 through 24 May 2019
ER -