Trajectory Prediction via Bayesian Intention Inference under Unknown Goals and Kinematics

2025-09-29

AI Summary

To address the challenge of real-time trajectory prediction under unknown and dynamically evolving target intent and motion characteristics, this paper proposes a model-free, adaptive Bayesian intent inference framework. The method jointly estimates latent Markovian intent states and shortest-path-following parameters via adaptive Bayesian filtering, enabling online, coupled inference of intent and dynamics—supporting abrupt intent switches and unmodeled dynamic responses without requiring prior behavioral models or offline training. Integrating sample-based trajectory prediction with rigorous uncertainty quantification, the approach is validated on hardware platforms including quadrotor and quadruped robots, achieving a real-time execution frequency of 270 Hz. Monte Carlo evaluations (500 trials) and physical experiments demonstrate significant improvements in prediction accuracy and robustness over both non-adaptive and partially adaptive baseline methods.

Technology Category

• Intelligent Robots: State Estimation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems

Abstract

This work introduces an adaptive Bayesian algorithm for real-time trajectory prediction via intention inference, where a target's intentions and motion characteristics are unknown and subject to change. The method concurrently estimates two critical variables: the target's current intention, modeled as a Markovian latent state, and an intention parameter that describes the target's adherence to a shortest-path policy. By integrating this joint update technique, the algorithm maintains robustness against abrupt intention shifts and unknown motion dynamics. A sampling-based trajectory prediction mechanism then exploits these adaptive estimates to generate probabilistic forecasts with quantified uncertainty. We validate the framework through numerical experiments: Ablation studies of two cases, and a 500-trial Monte Carlo analysis; Hardware demonstrations on quadrotor and quadrupedal platforms. Experimental results demonstrate that the proposed approach significantly outperforms non-adaptive and partially adaptive methods. The method operates in real time around 270 Hz without requiring training or detailed prior knowledge of target behavior, showcasing its applicability in various robotic systems.

Problem

• Predicts target trajectories under unknown intentions and motion dynamics
• Estimates latent intentions and path-following parameters concurrently
• Generates probabilistic forecasts robust to sudden intention changes

Innovation

• Bayesian algorithm for real-time intention inference
• Joint estimation of intention and motion parameters
• Sampling-based probabilistic trajectory prediction with uncertainty