Reliable Trajectories for Dynamic Quadrupeds using Analytical Costs and Learned Initializations

Dynamic traversal of uneven terrain is a major objective in the field of legged robotics. The most recent model predictive control approaches for these systems can generate robust dynamic motion of short duration; however, planning over a longer time horizon may be necessary when navigating complex terrain. A recently-developed framework, Trajectory Optimization for Walking Robots (TOWR), computes such plans but does not guarantee their reliability on real platforms, under uncertainty and perturbations. We extend TOWR with analytical costs to generate trajectories that a state-of-the-art whole-body tracking controller can successfully execute. To reduce online computation time, we implement a learning-based scheme for initialization of the nonlinear program based on offline experience. The execution of trajectories as long as 16 footsteps and 5.5 s over different terrains by a real quadruped demonstrates the effectiveness of the approach on hardware. This work builds toward an online system which can efficiently and robustly replan dynamic trajectories.

[1]  Alexander Herzog,et al.  A convex model of humanoid momentum dynamics for multi-contact motion generation , 2016, 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids).

[2]  Emanuel Todorov,et al.  Trajectory optimization for domains with contacts using inverse dynamics , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Peter Fankhauser,et al.  Perception-less terrain adaptation through whole body control and hierarchical optimization , 2016, 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids).

[4]  WächterAndreas,et al.  On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming , 2006 .

[5]  Zoran Popovic,et al.  Discovery of complex behaviors through contact-invariant optimization , 2012, ACM Trans. Graph..

[6]  Hannes Sommer,et al.  The Two-State Implicit Filter Recursive Estimation for Mobile Robots , 2018, IEEE Robotics and Automation Letters.

[7]  Marco Hutter,et al.  Gait and Trajectory Optimization for Legged Systems Through Phase-Based End-Effector Parameterization , 2018, IEEE Robotics and Automation Letters.

[8]  Darwin G. Caldwell,et al.  Trajectory and foothold optimization using low-dimensional models for rough terrain locomotion , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[9]  Sergey Levine,et al.  Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics , 2014, NIPS.

[10]  Olivier Stasse,et al.  Using a Memory of Motion to Efficiently Warm-Start a Nonlinear Predictive Controller , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[11]  Vladimir Ivan,et al.  Leveraging Precomputation with Problem Encoding for Warm-Starting Trajectory Optimization in Complex Environments , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[12]  John T. Betts,et al.  Practical Methods for Optimal Control and Estimation Using Nonlinear Programming , 2009 .

[13]  Pierre-Brice Wieber,et al.  Fast Direct Multiple Shooting Algorithms for Optimal Robot Control , 2005 .

[14]  Anil V. Rao,et al.  Practical Methods for Optimal Control Using Nonlinear Programming , 1987 .

[15]  Christopher G. Atkeson,et al.  Transfer of policies based on trajectory libraries , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  Lorenz T. Biegler,et al.  On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming , 2006, Math. Program..

[17]  Marco Hutter,et al.  Dynamic Locomotion on Slippery Ground , 2019, IEEE Robotics and Automation Letters.

[18]  Emanuel Todorov,et al.  A convex, smooth and invertible contact model for trajectory optimization , 2011, 2011 IEEE International Conference on Robotics and Automation.

[19]  Gerd Hirzinger,et al.  Trajectory planning for optimal robot catching in real-time , 2011, 2011 IEEE International Conference on Robotics and Automation.

[20]  Olivier Stasse,et al.  A versatile and efficient pattern generator for generalized legged locomotion , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[21]  Marc Toussaint,et al.  Fast motion planning from experience: trajectory prediction for speeding up movement generation , 2013, Auton. Robots.

[22]  Russ Tedrake,et al.  A direct method for trajectory optimization of rigid bodies through contact , 2014, Int. J. Robotics Res..

[23]  Sylvain Calinon,et al.  Memory of Motion for Warm-Starting Trajectory Optimization , 2019, IEEE Robotics and Automation Letters.

[24]  Marco Hutter,et al.  Dynamic Locomotion Through Online Nonlinear Motion Optimization for Quadrupedal Robots , 2018, IEEE Robotics and Automation Letters.

[25]  Dmitry Berenson,et al.  A robot path planning framework that learns from experience , 2012, 2012 IEEE International Conference on Robotics and Automation.

[26]  Siddhartha S. Srinivasa,et al.  Learning from Experience in Manipulation Planning: Setting the Right Goals , 2011, ISRR.