CNNs based Foothold Selection for Energy-Efficient Quadruped Locomotion over Rough Terrains

When deployed in practical scenario, the legged robot has higher terrain passing ability but is suffering from lower locomotion efficiency than the wheeled robot. In this paper, we present a strategy that can improve the locomotion efficiency for a quadrupedal robot. First, an optimized energy-efficient nominal stance is generated. Second, a Convolutional Neural Networks (CNNs) based and self-supervised foothold classifier is implemented which will guide the robot to form the supporting legs in energy-efficient nominal stance during locomotion. The effectiveness of the present approach is validated on our quadrupedal robot Pegasus in stairs climbing experiment.

[1]  Hannes Sommer,et al.  Quadrupedal locomotion using hierarchical operational space control , 2014, Int. J. Robotics Res..

[2]  R. McGhee,et al.  On the stability properties of quadruped creeping gaits , 1968 .

[3]  Roland Siegwart,et al.  Navigation planning for legged robots in challenging terrain , 2016, IROS 2016.

[4]  Albert Wang,et al.  Design principles for highly efficient quadrupeds and implementation on the MIT Cheetah robot , 2013, 2013 IEEE International Conference on Robotics and Automation.

[5]  Nico Roos,et al.  An energy efficient dynamic gait for a Nao robot , 2014, 2014 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC).

[6]  Navinda Kottege,et al.  Weaver: Hexapod robot for autonomous navigation on unstructured terrain , 2018, J. Field Robotics.

[7]  Hsiu-Chin Lin,et al.  Single-shot Foothold Selection and Constraint Evaluation for Quadruped Locomotion , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[8]  Rüdiger Dillmann,et al.  Six-legged walking in rough terrain based on foot point planning , 2009 .

[9]  Stefan Schaal,et al.  A Robust Quadruped Walking Gait for Traversing Rough Terrain , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[10]  R. Siegwart,et al.  Efficient and Versatile Locomotion With Highly Compliant Legs , 2013, IEEE/ASME Transactions on Mechatronics.

[11]  C. David Remy,et al.  Optimal gaits and motions for legged robots , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[12]  Robert Wittmann,et al.  Fast object approximation for real-time 3D obstacle avoidance with biped robots , 2016, 2016 IEEE International Conference on Advanced Intelligent Mechatronics (AIM).

[13]  Reid G. Simmons,et al.  Perception, Planning, and Control for Autonomous Walking With the Ambler Planetary Rover , 1996, Int. J. Robotics Res..

[14]  Andrew Y. Ng,et al.  A control architecture for quadruped locomotion over rough terrain , 2008, 2008 IEEE International Conference on Robotics and Automation.

[15]  Darwin G. Caldwell,et al.  Fast and Continuous Foothold Adaptation for Dynamic Locomotion Through CNNs , 2018, IEEE Robotics and Automation Letters.

[16]  Stefan Schaal,et al.  Learning locomotion over rough terrain using terrain templates , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[17]  Tad McGeer,et al.  Passive Dynamic Walking , 1990, Int. J. Robotics Res..

[18]  Peter Fankhauser,et al.  Robust Rough-Terrain Locomotion with a Quadrupedal Robot , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Darwin G. Caldwell,et al.  Reactive trotting with foot placement corrections through visual pattern classification , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[20]  Edin Koco.  Locomotion Control for Electrically Powered Quadruped Robot Dynarobin , 2014 .

[21]  Jonathan E. Clark,et al.  Energy Efficient Navigation for Running Legged Robots , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[22]  Peter Fankhauser,et al.  ANYmal - a highly mobile and dynamic quadrupedal robot , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).