Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logic
This addresses motion planning for autonomous systems with complex temporal specifications, but it is incremental as it builds on existing reinforcement learning and automata methods.
The paper tackles motion planning for autonomous systems with unknown dynamics and continuous spaces by using linear temporal logic (LTL) to specify tasks, converting them into automata, and designing a model-free reinforcement learning framework with reward shaping to maximize satisfaction probability. It demonstrates performance in OpenAI gym environments, though no concrete numbers are provided.
This paper investigates the motion planning of autonomous dynamical systems modeled by Markov decision processes (MDP) with unknown transition probabilities over continuous state and action spaces. Linear temporal logic (LTL) is used to specify high-level tasks over infinite horizon, which can be converted into a limit deterministic generalized Büchi automaton (LDGBA) with several accepting sets. The novelty is to design an embedded product MDP (EP-MDP) between the LDGBA and the MDP by incorporating a synchronous tracking-frontier function to record unvisited accepting sets of the automaton, and to facilitate the satisfaction of the accepting conditions. The proposed LDGBA-based reward shaping and discounting schemes for the model-free reinforcement learning (RL) only depend on the EP-MDP states and can overcome the issues of sparse rewards. Rigorous analysis shows that any RL method that optimizes the expected discounted return is guaranteed to find an optimal policy whose traces maximize the satisfaction probability. A modular deep deterministic policy gradient (DDPG) is then developed to generate such policies over continuous state and action spaces. The performance of our framework is evaluated via an array of OpenAI gym environments.