Enhanced Visual SLAM for Collision-free Driving with Lightweight Autonomous Cars

TL;DR

This paper introduces a vision-based obstacle avoidance system for lightweight autonomous cars that combines enhanced visual perception with advanced path planning to achieve safe, stable, and efficient navigation using only a CPU and a single RGB-D camera.

Contribution

It develops a novel obstacle avoidance strategy integrating enhanced ORBSLAM3 with optical flow and a CLF-CBF-QP based path planning method with obstacle shape reconstruction, suitable for CPU-only devices.

Findings

Effectively avoids obstacles in complex indoor environments

Outperforms benchmark algorithms in trajectory stability and length

Demonstrates robustness and efficiency in simulation

Abstract

The paper presents a vision-based obstacle avoidance strategy for lightweight self-driving cars that can be run on a CPU-only device using a single RGB-D camera. The method consists of two steps: visual perception and path planning. The visual perception part uses ORBSLAM3 enhanced with optical flow to estimate the car's poses and extract rich texture information from the scene. In the path planning phase, we employ a method combining a control Lyapunov function and control barrier function in the form of quadratic program (CLF-CBF-QP) together with an obstacle shape reconstruction process (SRP) to plan safe and stable trajectories. To validate the performance and robustness of the proposed method, simulation experiments were conducted with a car in various complex indoor environments using the Gazebo simulation environment. Our method can effectively avoid obstacles in the scenes. The proposed algorithm outperforms benchmark algorithms in achieving more stable and shorter trajectories across multiple simulated scenes.