Poly-Autoregressive Prediction for Modeling Interactions
원문 초록
We introduce a simple framework for predicting the behavior of an agent in multi-agent settings. In contrast to autoregressive (AR) tasks, such as language processing, our focus is on scenarios with multiple agents whose interactions are shaped by physical constraints and internal motivations. To this end, we propose Poly-Autoregressive (PAR) modeling, which forecasts an ego agent's future behavior by reasoning about the ego agent's state history and the past and current states of other interacting agents. At its core, PAR represents the behavior of all agents as a sequence of tokens, each representing an agent's state at a specific timestep. With minimal data pre-processing changes, we show that PAR can be applied to three different problems: human action forecasting in social situations, trajectory prediction for autonomous vehicles, and object pose forecasting during hand-object interaction. Using a small proof-of-concept transformer backbone, PAR outperforms AR across these three scenarios. The project website can be found at https://neerja.me/PAR/.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Where, What, Why: Towards Explainable Driver Attention Prediction
Trajectory Prediction Meets Large Language Models: A Survey
Multi-Strategy Improved Snake Optimizer Accelerated CNN-LSTM-Attention-Adaboost for Trajectory Prediction
GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory Prediction
Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Review
TrajFlow: Multi-modal Motion Prediction via Flow Matching
토론
이 논문과 연결된 포럼 글이 아직 없습니다.