Scaling Sampling-based Motion Planning to Humanoid Robots
This work addresses motion planning challenges for humanoid robots, which is crucial for their deployment in real-world tasks, but it is incremental as it builds on existing sampling-based algorithms with specific adaptations.
The paper tackles the problem of planning balanced and collision-free motion for humanoid robots in complex environments by proposing a method that adapts existing sampling-based algorithms with customized state representation, biased sampling, and a robust inverse kinematics solver, enabling successful trajectory generation for a 38 degrees-of-freedom robot like NASA Valkyrie without prior offline computation.
Planning balanced and collision-free motion for humanoid robots is non-trivial, especially when they are operated in complex environments, such as reaching targets behind obstacles or through narrow passages. We propose a method that allows us to apply existing sampling--based algorithms to plan trajectories for humanoids by utilizing a customized state space representation, biased sampling strategies, and a steering function based on a robust inverse kinematics solver. Our approach requires no prior offline computation, thus one can easily transfer the work to new robot platforms. We tested the proposed method solving practical reaching tasks on a 38 degrees-of-freedom humanoid robot, NASA Valkyrie, showing that our method is able to generate valid motion plans that can be executed on advanced full-size humanoid robots. We also present a benchmark between different motion planning algorithms evaluated on a variety of reaching motion problems. This allows us to find suitable algorithms for solving humanoid motion planning problems, and to identify the limitations of these algorithms.