RAY-TOLD: Ray-Based Latent Dynamics for Dense Dynamic Obstacle Avoidance with TDMPC

TL;DR

RAY-TOLD is a hybrid control approach that combines obstacle-aware latent dynamics with MPPI and reinforcement learning to improve dense dynamic obstacle avoidance for mobile robots.

Contribution

It introduces a LiDAR-based latent dynamics model and a policy mixture sampling strategy to enhance long-horizon planning in dynamic environments.

Findings

Outperforms MPPI baseline in high-density obstacle scenarios

Reduces collision rate in stochastic dynamic environments

Enhances navigation safety and reliability through hybrid planning

Abstract

Dense, dynamic crowds pose a persistent challenge for autonomous mobile robots. Purely reactive planning methods, such as Model Predictive Path Integral (MPPI) control, often fail to escape local minima in complex scenarios due to their limited prediction horizon. To bridge this gap, we propose Ray-based Task-Oriented Latent Dynamics (RAY-TOLD), a hybrid control architecture that integrates obstacle information into latent dynamics and utilizes the robustness of physics-based MPPI with the long-horizon foresight of reinforcement learning. RAY-TOLD leverages a LiDAR-centric latent dynamics model to encode high-dimensional sensor data into a compact state representation, enabling the learning of a terminal value function and a policy prior. We introduce a policy mixture sampling strategy that augments the MPPI candidate population with trajectories derived from the learned policy, effectively guiding the planner towards the goal while maintaining kinematic feasibility. Extensive tests in a stochastic environment with high-density dynamic obstacles demonstrate that our method outperforms the MPPI baseline, reducing the collision rate. The results confirm that blending short-horizon physics-based rollouts with learned long-horizon intent significantly enhances navigation reliability and safety.