Proactive Local-Minima-Free Robot Navigation: Blending Motion Prediction with Safe Control

TL;DR

This paper presents a novel framework combining motion prediction and adaptive safe control to enable robots to navigate safely and efficiently in complex, dynamic environments with moving obstacles.

Contribution

It introduces an online learning pipeline for barrier functions from multimodal obstacle predictions and an autonomous parameter tuning algorithm for adaptive safe control.

Findings

Outperforms baseline methods in safety and efficiency.

Successfully tested in real-world crowded environments.

Demonstrates robustness to obstacle prediction errors.

Abstract

This work addresses the challenge of safe and efficient mobile robot navigation in complex dynamic environments with concave moving obstacles. Reactive safe controllers like Control Barrier Functions (CBFs) design obstacle avoidance strategies based only on the current states of the obstacles, risking future collisions. To alleviate this problem, we use Gaussian processes to learn barrier functions online from multimodal motion predictions of obstacles generated by neural networks trained with energy-based learning. The learned barrier functions are then fed into quadratic programs using modulated CBFs (MCBFs), a local-minimum-free version of CBFs, to achieve safe and efficient navigation. The proposed framework makes two key contributions. First, it develops a prediction-to-barrier function online learning pipeline. Second, it introduces an autonomous parameter tuning algorithm that adapts MCBFs to deforming, prediction-based barrier functions. The framework is evaluated in both simulations and real-world experiments, consistently outperforming baselines and demonstrating superior safety and efficiency in crowded dynamic environments.