Title | ||
---|---|---|
Safe-To-Explore State Spaces: Ensuring Safe Exploration In Policy Search With Hierarchical Task Optimization |
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. |
Year | Venue | Field |
---|---|---|
2018 | 2018 IEEE-RAS 18TH INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS (HUMANOIDS) | Kernel (linear algebra),Ranking,Computer science,Simulation,Harm,Collision,Human–computer interaction,Artificial intelligence,Robot,Robotics,Reinforcement learning |
DocType | Volume | ISSN |
Journal | abs/1810.03516 | 2164-0572 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jens Lundell | 1 | 5 | 4.13 |
Robert Krug | 2 | 21 | 5.59 |
Erik Schaffernicht | 3 | 2 | 1.74 |
Todor Stoyanov | 4 | 260 | 26.07 |
V. Kyrki | 5 | 652 | 61.79 |