OGMP: Oracle Guided Multimodal Policies for Agile and Versatile Robot Control
CoRR(2024)
摘要
Amidst task-specific learning-based control synthesis frameworks that achieve
impressive empirical results, a unified framework that systematically
constructs an optimal policy for sufficiently solving a general notion of a
task is absent. Hence, we propose a theoretical framework for a task-centered
control synthesis leveraging two critical ideas: 1) oracle-guided policy
optimization for the non-limiting integration of sub-optimal task-based priors
to guide the policy optimization and 2) task-vital multimodality to break down
solving a task into executing a sequence of behavioral modes. The proposed
approach results in highly agile parkour and diving on a 16-DoF dynamic bipedal
robot. The obtained policy advances indefinitely on a track, performing leaps
and jumps of varying lengths and heights for the parkour task. Corresponding to
the dive task, the policy demonstrates front, back, and side flips from various
initial heights. Finally, we introduce a novel latent mode space reachability
analysis to study our policies' versatility and generalization by computing a
feasible mode set function through which we certify a set of failure-free modes
for our policy to perform at any given state.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要