Problem
Research questions and friction points this paper is trying to address.
Autonomous Navigation
Dynamic Environments
Multi-Sensor Perception
Collision Avoidance
Environmental Representation
Memory-Aware Multi-Sensor Perception for Efficient and Safe Navigation in Dynamic Environments
🤖 AI Summary
This study addresses the challenge of safe navigation in unknown dynamic environments where perception is limited and historical structural information is difficult to exploit. To this end, we propose a memory-aware framework that fuses LiDAR and RGB multi-source sensing to construct persistent environmental representations through online distance field representation learning. Building upon this representation, a stage-adaptive control barrier function quadratic programming (MCBF-QP) controller is designed to enable safety-critical decision-making. Experimental results demonstrate that the proposed framework significantly improves both navigation efficiency and goal-reaching rates in complex scenarios while rigorously guaranteeing obstacle avoidance safety.
📝 Abstract
Autonomous navigation in previously unseen environments requires effective perception, persistent environmental representation, and collision avoidance while maintaining progress toward a goal. Existing perception-based methods often rely on prior maps or short-horizon observations, limiting their ability to exploit previously observed structure. We propose a memory-aware multi-sensor navigation framework that integrates LiDAR and RGB perception, online distance-field representation learning, and a stage-adaptive Modulated Control Barrier Function Quadratic Program (MCBF-QP). The framework persistently represents static infrastructure while tracking dynamic obstacles, enabling the MCBF-QP controller to exploit previously observed geometry for obstacle circumvention and adapt its safety constraints and guidance to local conditions. Experiments in complex indoor and outdoor environments demonstrate improved navigation efficiency and goal-reaching performance while maintaining collision avoidance in narrow passages and around dynamic obstacles.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Memory-Aware Navigation
Multi-Sensor Fusion
Distance-Field Representation
Control Barrier Function
Dynamic Obstacle Avoidance
🔎 Similar Papers
No similar papers found.
