Future-Oriented Navigation: Dynamic Obstacle Avoidance with One-Shot Energy-Based Multimodal Motion Prediction

2025-05-01

AI Summary

To address safe navigation for mobile robots in dynamic and uncertain environments, this paper proposes a proactive obstacle avoidance framework integrating single-shot multimodal motion prediction with geometrically constrained model predictive control (MPC). The method introduces three key innovations: (1) an energy-based neural network enabling high-resolution, single-shot multi-step motion prediction; (2) an unsupervised proximity grouping mechanism that adaptively fuses motion predictions across multiple obstacles; and (3) an MPC optimizer with explicit geometric constraint embedding, balancing safety guarantees and real-time performance. Extensive experiments in representative warehouse scenarios demonstrate that the proposed approach significantly outperforms state-of-the-art dynamic obstacle avoidance methods—achieving superior path safety, planning frequency (>10 Hz), and task success rate—while exhibiting strong generalization across diverse operational settings.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Natural Language Processing: Safety and Robustness
• Humans and AI: Human-Aware Planning and Behavior Prediction

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
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

This paper proposes an integrated approach for the safe and efficient control of mobile robots in dynamic and uncertain environments. The approach consists of two key steps: one-shot multimodal motion prediction to anticipate motions of dynamic obstacles and model predictive control to incorporate these predictions into the motion planning process. Motion prediction is driven by an energy-based neural network that generates high-resolution, multi-step predictions in a single operation. The prediction outcomes are further utilized to create geometric shapes formulated as mathematical constraints. Instead of treating each dynamic obstacle individually, predicted obstacles are grouped by proximity in an unsupervised way to improve performance and efficiency. The overall collision-free navigation is handled by model predictive control with a specific design for proactive dynamic obstacle avoidance. The proposed approach allows mobile robots to navigate effectively in dynamic environments. Its performance is accessed across various scenarios that represent typical warehouse settings. The results demonstrate that the proposed approach outperforms other existing dynamic obstacle avoidance methods.

Problem

• Safe and efficient control of mobile robots in dynamic environments
• One-shot multimodal motion prediction for dynamic obstacles
• Proactive collision avoidance using model predictive control

Innovation

• One-shot energy-based neural motion prediction
• Unsupervised proximity grouping of obstacles
• Model predictive control for collision avoidance