Self-Supervised Learning-Based Path Planning and Obstacle Avoidance Using PPO and B-Splines in Unknown Environments

TL;DR

This paper presents SmartBSP, a self-supervised learning framework combining PPO and B-splines for real-time path planning and obstacle avoidance in unknown environments, validated through simulations and real-world experiments.

Contribution

It introduces a novel self-supervised learning approach integrating PPO, CNN, and B-splines for autonomous navigation in complex, unknown environments.

Findings

Demonstrates robustness across diverse scenarios

Shows effective obstacle avoidance and path optimization

Validates real-time performance with ROS experiments

Abstract

This paper introduces SmartBSP, an advanced self-supervised learning framework for real-time path planning and obstacle avoidance in autonomous robotics navigating through complex environments. The proposed system integrates Proximal Policy Optimization (PPO) with Convolutional Neural Networks (CNN) and Actor-Critic architecture to process limited LIDAR inputs and compute spatial decision-making probabilities. The robot's perceptual field is discretized into a grid format, which the CNN analyzes to produce a spatial probability distribution. During the training process a nuanced cost function is minimized that accounts for path curvature, endpoint proximity, and obstacle avoidance. Simulations results in different scenarios validate the algorithm's resilience and adaptability across diverse operational scenarios. Subsequently, Real-time experiments, employing the Robot Operating System (ROS), were carried out to assess the efficacy of the proposed algorithm.