Co-learning Planning and Control Policies Constrained by Differentiable Logic Specifications
This addresses the challenge of training robotics policies with complex specifications, offering incremental improvements in sample efficiency and specification handling.
The paper tackles the problem of synthesizing planning and control policies for high-dimensional robot navigation with complex logic specifications, resulting in significantly reduced sample complexity and efficient generation of long-horizon motion paths across different map layouts.
Synthesizing planning and control policies in robotics is a fundamental task, further complicated by factors such as complex logic specifications and high-dimensional robot dynamics. This paper presents a novel reinforcement learning approach to solving high-dimensional robot navigation tasks with complex logic specifications by co-learning planning and control policies. Notably, this approach significantly reduces the sample complexity in training, allowing us to train high-quality policies with much fewer samples compared to existing reinforcement learning algorithms. In addition, our methodology streamlines complex specification extraction from map images and enables the efficient generation of long-horizon robot motion paths across different map layouts. Moreover, our approach also demonstrates capabilities for high-dimensional control and avoiding suboptimal policies via policy alignment. The efficacy of our approach is demonstrated through experiments involving simulated high-dimensional quadruped robot dynamics and a real-world differential drive robot (TurtleBot3) under different types of task specifications.