用多智能体状态序列建模交互行为，提升预测精度。
Poly-Autoregressive Prediction for Modeling Interactions
- 将所有智能体状态转为时间序列令牌，统一建模交互
- 在三类场景中均优于传统自回归方法
- 适合需要理解复杂交互的机器人与自动驾驶应用
我们提出一种简单框架，用于预测多智能体环境中的代理行为。不同于语言处理等传统自回归任务，本研究关注受物理约束和内在动机影响的多智能体交互。为此，我们引入多自回归（Poly-Autoregressive, PAR）建模：通过分析自身历史状态及其它代理的过去和当前状态，预测主体未来行为。PAR将所有智能体的行为表示为一系列令牌，每个令牌代表某一时刻某智能体的状态。仅需少量数据预处理改动，PAR即可应用于三类任务：社交情境中的人类动作预测、自动驾驶车辆轨迹预测，以及手物交互中的物体姿态预测。采用小型Transformer骨干网络，PAR在三类任务中均优于标准自回归方法。项目主页见 https://neerja.me/PAR/。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。