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

2026-01-15

AI Summary

This work proposes a safe navigation framework for mobile robots operating in complex environments with concave dynamic obstacles, addressing the collision risks and local minima that arise from relying solely on current-state obstacle avoidance. The approach integrates multimodal motion prediction with an adaptive barrier function: a neural network based on energy-based learning forecasts future obstacle trajectories, while a Gaussian process enables online learning of deformable predictive barrier functions. These are embedded within a modulation-based control barrier function (MCBF) framework that guarantees no local minima under safety constraints. An online learning pipeline coupled with an automatic parameter tuning mechanism allows the system to adapt to dynamic environmental changes. Extensive simulations and real-world experiments demonstrate that the proposed method significantly outperforms existing baselines in crowded dynamic scenarios, achieving simultaneous improvements in both safety and navigation efficiency.

Technology Category

• Natural Language Processing: Safety and Robustness
• Intelligent Robots: Motion and Path Planning
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• robot navigation
• dynamic environments
• local minima
• collision avoidance
• concave obstacles

Innovation

• Control Barrier Functions
• Gaussian Processes
• Motion Prediction
• Local-Minima-Free Navigation
• Energy-Based Learning