AD-NODE: Adaptive Dynamics Learning with Neural ODEs for Mobile Robots Control

2025-10-06

AI Summary

Mobile robots face challenges in modeling dynamics and achieving online adaptability within perception-limited, uncertain environments. Method: This paper proposes an implicit environment-aware dynamics learning framework based on Neural Ordinary Differential Equations (Neural ODEs). It infers environmental dynamics implicitly from historical state-action sequences—without requiring explicit environmental observations—and introduces a novel two-stage training scheme to jointly optimize model parameters and latent variables, enabling seamless integration into Model Predictive Control (MPC). Results: Evaluated on simulated and real-world platforms—including a 2D differential-drive robot, a 3D quadrotor, and the Sphero BOLT—the method significantly improves target-reaching accuracy (average gain of 37.2%) and path-tracking robustness, demonstrating sustained adaptability under spatiotemporally varying environmental conditions.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Search and Optimization: Learning to Search
• 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
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Mobile robots, such as ground vehicles and quadrotors, are becoming increasingly important in various fields, from logistics to agriculture, where they automate processes in environments that are difficult to access for humans. However, to perform effectively in uncertain environments using model-based controllers, these systems require dynamics models capable of responding to environmental variations, especially when direct access to environmental information is limited. To enable such adaptivity and facilitate integration with model predictive control, we propose an adaptive dynamics model which bypasses the need for direct environmental knowledge by inferring operational environments from state-action history. The dynamics model is based on neural ordinary equations, and a two-phase training procedure is used to learn latent environment representations. We demonstrate the effectiveness of our approach through goal-reaching and path-tracking tasks on three robotic platforms of increasing complexity: a 2D differential wheeled robot with changing wheel contact conditions, a 3D quadrotor in variational wind fields, and the Sphero BOLT robot under two contact conditions for real-world deployment. Empirical results corroborate that our method can handle temporally and spatially varying environmental changes in both simulation and real-world systems.

Problem

• Developing adaptive dynamics models for robots in uncertain environments
• Inferring operational environments from state-action history without direct knowledge
• Handling varying environmental changes across different robotic platforms

Innovation

• Adaptive dynamics model using Neural ODEs
• Two-phase training for latent environment representations
• Inferring operational environments from state-action history