Trajectory prediction for heterogeneous agents: A performance analysis on small and imbalanced datasets

2025-10-04

AI Summary

Trajectory and intent prediction for heterogeneous agents (e.g., robots) in complex dynamic environments remains challenging under few-shot learning and class-imbalanced data conditions. Method: This paper proposes a lightweight, category-condition-aware prediction framework. It systematically analyzes how categorical conditions affect predictive uncertainty and introduces a hybrid baseline model integrating pattern-driven reasoning with deep learning—combining conditional pattern modeling and a lightweight neural network. Experiments are conducted on THÖR-MAGNI and the Stanford Drone Dataset for category-aware trajectory prediction. Contribution/Results: Explicit incorporation of categorical labels significantly improves prediction accuracy. Pattern-driven components demonstrate superior robustness over purely data-driven deep learning models under data scarcity or skewed class distributions. The framework delivers an interpretable, data-efficient, and low-dependency prediction paradigm tailored for resource-constrained multi-agent navigation systems.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Adversarial Agents
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Robots and other intelligent systems navigating in complex dynamic environments should predict future actions and intentions of surrounding agents to reach their goals efficiently and avoid collisions. The dynamics of those agents strongly depends on their tasks, roles, or observable labels. Class-conditioned motion prediction is thus an appealing way to reduce forecast uncertainty and get more accurate predictions for heterogeneous agents. However, this is hardly explored in the prior art, especially for mobile robots and in limited data applications. In this paper, we analyse different class-conditioned trajectory prediction methods on two datasets. We propose a set of conditional pattern-based and efficient deep learning-based baselines, and evaluate their performance on robotics and outdoors datasets (THÖR-MAGNI and Stanford Drone Dataset). Our experiments show that all methods improve accuracy in most of the settings when considering class labels. More importantly, we observe that there are significant differences when learning from imbalanced datasets, or in new environments where sufficient data is not available. In particular, we find that deep learning methods perform better on balanced datasets, but in applications with limited data, e.g., cold start of a robot in a new environment, or imbalanced classes, pattern-based methods may be preferable.

Problem

• Predicting trajectories for heterogeneous agents in dynamic environments
• Analyzing class-conditioned prediction methods on imbalanced datasets
• Evaluating performance in limited data scenarios for robotics

Innovation

• Class-conditioned trajectory prediction for heterogeneous agents
• Pattern-based and deep learning baselines comparison
• Evaluation on robotics and outdoor datasets performance