SABER: Data-Driven Motion Planner for Autonomously Navigating Heterogeneous Robots
This work addresses navigation challenges for heterogeneous robots in uncertain settings, representing an incremental improvement through integration of existing methods.
The authors tackled motion planning for heterogeneous robot teams in uncertain environments by combining stochastic model predictive control, recurrent neural networks for uncertainty estimation, and Deep Q-learning for high-level path planning, demonstrating the approach on ground and aerial robots with code provided.
We present an end-to-end online motion planning framework that uses a data-driven approach to navigate a heterogeneous robot team towards a global goal while avoiding obstacles in uncertain environments. First, we use stochastic model predictive control (SMPC) to calculate control inputs that satisfy robot dynamics, and consider uncertainty during obstacle avoidance with chance constraints. Second, recurrent neural networks are used to provide a quick estimate of future state uncertainty considered in the SMPC finite-time horizon solution, which are trained on uncertainty outputs of various simultaneous localization and mapping algorithms. When two or more robots are in communication range, these uncertainties are then updated using a distributed Kalman filtering approach. Lastly, a Deep Q-learning agent is employed to serve as a high-level path planner, providing the SMPC with target positions that move the robots towards a desired global goal. Our complete methods are demonstrated on a ground and aerial robot simultaneously (code available at: https://github.com/AlexS28/SABER).