English

Safe-To-Explore State Spaces: Ensuring Safe Exploration in Policy Search with Hierarchical Task Optimization

Robotics 2018-10-09 v1

Abstract

Policy search reinforcement learning allows robots to acquire skills by themselves. However, the learning procedure is inherently unsafe as the robot has no a-priori way to predict the consequences of the exploratory actions it takes. Therefore, exploration can lead to collisions with the potential to harm the robot and/or the environment. In this work we address the safety aspect by constraining the exploration to happen in safe-to-explore state spaces. These are formed by decomposing target skills (e.g., grasping) into higher ranked sub-tasks (e.g., collision avoidance, joint limit avoidance) and lower ranked movement tasks (e.g., reaching). Sub-tasks are defined as concurrent controllers (policies) in different operational spaces together with associated Jacobians representing their joint-space mapping. Safety is ensured by only learning policies corresponding to lower ranked sub-tasks in the redundant null space of higher ranked ones. As a side benefit, learning in sub-manifolds of the state-space also facilitates sample efficiency. Reaching skills performed in simulation and grasping skills performed on a real robot validate the usefulness of the proposed approach.

Keywords

Cite

@article{arxiv.1810.03516,
  title  = {Safe-To-Explore State Spaces: Ensuring Safe Exploration in Policy Search with Hierarchical Task Optimization},
  author = {Jens Lundell and Robert Krug and Erik Schaffernicht and Todor Stoyanov and Ville Kyrki},
  journal= {arXiv preprint arXiv:1810.03516},
  year   = {2018}
}

Comments

In 2018 IEEE-RAS International Conference on Humanoid Robots (Humanoids), Beijing, China

R2 v1 2026-06-23T04:32:16.604Z