Multi-controller multi-objective locomotion planning for legged robots

Different legged robot locomotion controllers offer different advantages; from speed of motion to energy, computational demand, safety and others. In this paper we propose a method for planning locomotion with multiple controllers and sub-planners, explicitly considering the multi-objective nature of the legged locomotion planning problem. The planner first obtains body paths extended with a choice of controller or sub-planner, and then fills the gaps by sub-planning. The method leads to paths with a mix of static and dynamic walking which only plan footsteps where necessary. We show that our approach is faster than pure footstep planning methods both in computation (2x) and mission time (1.4x), and safer than pure dynamic-walking methods. In addition, we propose two methods for aggregating the multiple objectives in search-based planning and reach desirable trade-offs without weight tuning. We show that they reach desirable Pareto-optimal solutions up to 8x faster than fairly-tuned traditional weighted-sum methods. Our conclusions are drawn from a combination of planning, physics simulation, and real robot experiments.

[1]  Christopher G. Atkeson,et al.  Optimization‐based Full Body Control for the DARPA Robotics Challenge , 2015, J. Field Robotics.

[2]  Hemant Kumar Rath,et al.  Realistic indoor path loss modeling for regular WiFi operations in India , 2017, 2017 Twenty-third National Conference on Communications (NCC).

[3]  Timothy Bretl,et al.  Using Motion Primitives in Probabilistic Sample-Based Planning for Humanoid Robots , 2008, WAFR.

[4]  Razvan Pascanu,et al.  Policy Distillation , 2015, ICLR.

[5]  Peter Fankhauser,et al.  ANYmal - a highly mobile and dynamic quadrupedal robot , 2016, IROS 2016.

[6]  Dmitry Berenson,et al.  Humanoid Navigation Planning in Large Unstructured Environments Using Traversability - Based Segmentation , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[7]  Chonhyon Park,et al.  An Efficient Acyclic Contact Planner for Multiped Robots , 2018, IEEE Transactions on Robotics.

[8]  Atsuo Takanishi,et al.  Footstep Planning for Slippery and Slanted Terrain Using Human-Inspired Models , 2016, IEEE Transactions on Robotics.

[9]  Andrew Howard,et al.  Design and use paradigms for Gazebo, an open-source multi-robot simulator , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[10]  Abderrahmane Kheddar,et al.  Multi-contact walking pattern generation based on model preview control of 3D COM accelerations , 2016, 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids).

[11]  Aaron D. Ames,et al.  Footstep and motion planning in semi-unstructured environments using randomized possibility graphs , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[12]  Pieter Abbeel,et al.  Meta Learning Shared Hierarchies , 2017, ICLR.

[13]  Atsuo Takanishi,et al.  Gait planning for biped locomotion on slippery terrain , 2014, 2014 IEEE-RAS International Conference on Humanoid Robots.

[14]  Carlos Mastalli,et al.  Simultaneous Contact, Gait, and Motion Planning for Robust Multilegged Locomotion via Mixed-Integer Convex Optimization , 2017, IEEE Robotics and Automation Letters.

[15]  Darwin G. Caldwell,et al.  Hierarchical planning of dynamic movements without scheduled contact sequences , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[16]  Siddhartha S. Srinivasa,et al.  A framework for extreme locomotion planning , 2012, 2012 IEEE International Conference on Robotics and Automation.

[17]  Robin Deits,et al.  Computing Large Convex Regions of Obstacle-Free Space Through Semidefinite Programming , 2014, WAFR.

[18]  Maxim Likhachev,et al.  Path Planning with Adaptive Dimensionality , 2011, SOCS.

[19]  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).

[20]  Kaisa Miettinen,et al.  Introduction to Multiobjective Optimization: Noninteractive Approaches , 2008, Multiobjective Optimization.

[21]  Ioannis Havoutis,et al.  Contact Planning for the ANYmal Quadruped Robot using an Acyclic Reachability-Based Planner , 2019, TAROS.

[22]  Roland Siegwart,et al.  Practice Makes Perfect: An Optimization-Based Approach to Controlling Agile Motions for a Quadruped Robot , 2016, IEEE Robotics & Automation Magazine.

[23]  Alexander Lavin,et al.  A Pareto Optimal D* Search Algorithm for Multiobjective Path Planning , 2015, ArXiv.

[24]  Darwin G. Caldwell,et al.  Planning and execution of dynamic whole-body locomotion for a hydraulic quadruped on challenging terrain , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[25]  Renaud Dubé,et al.  Free Gait — An architecture for the versatile control of legged robots , 2016, 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids).

[26]  Robin Deits,et al.  Footstep planning on uneven terrain with mixed-integer convex optimization , 2014, 2014 IEEE-RAS International Conference on Humanoid Robots.

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

[28]  Pieter Abbeel,et al.  Stochastic Neural Networks for Hierarchical Reinforcement Learning , 2016, ICLR.

[29]  Siddhartha S. Srinivasa,et al.  Pareto-optimal search over configuration space beliefs for anytime motion planning , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[30]  Michael A. Goodrich,et al.  MORRF*: Sampling-Based Multi-Objective Motion Planning , 2015, IJCAI.

[31]  Sebastian Thrun,et al.  ARA*: Anytime A* with Provable Bounds on Sub-Optimality , 2003, NIPS.

[32]  Atsuo Takanishi,et al.  Material recognition CNNs and hierarchical planning for biped robot locomotion on slippery terrain , 2016, 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids).

[33]  Karthik Vijayakumar,et al.  A Single-Planner Approach to Multi-Modal Humanoid Mobility , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).