AMP: Autoregressive Motion Prediction Revisited with Next Token Prediction for Autonomous Driving
As an essential task in autonomous driving (AD), motion prediction aims to predict the future states of surround objects for navigation. One natural solution is to estimate the position of other agents in a step-by-step manner where each predicted time-step is conditioned on both observed time-steps and previously predicted time-steps, i.e., autoregressive prediction. Pioneering works like SocialLSTM and MFP design their decoders based on this intuition. However, almost all state-of-the-art works assume that all predicted time-steps are independent conditioned on observed time-steps, where they use a single linear layer to generate positions of all time-steps simultaneously. They dominate most motion prediction leaderboards due to the simplicity of training MLPs compared to autoregressive networks. In this paper, we introduce the GPT style next token prediction into motion forecasting. In this way, the input and output could be represented in a unified space and thus the autoregressive prediction becomes more feasible. However, different from language data which is composed of homogeneous units -words, the elements in the driving scene could have complex spatial-temporal and semantic relations. To this end, we propose to adopt three factorized attention modules with different neighbors for information aggregation and different position encoding styles to capture their relations, e.g., encoding the transformation between coordinate systems for spatial relativity while adopting RoPE for temporal relativity. Empirically, by equipping with the aforementioned tailored designs, the proposed method achieves state-of-the-art performance in the Waymo Open Motion and Waymo Interaction datasets. Notably, AMP outperforms other recent autoregressive motion prediction methods: MotionLM and StateTransformer, which demonstrates the effectiveness of the proposed designs.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingMotion Forecastingmotion predictionPositionPredictionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation
We present ScaleMoGen, a scale-wise autoregressive framework for text-driven human motion generation. Unlike conventional autoregressive approaches that rely on standard next-token prediction, ScaleMoGen frames motion ge…
Next-Scale Autoregressive Models for Text-to-Motion Generation
Autoregressive (AR) models offer stable and efficient training, but standard next-token prediction is not well aligned with the temporal structure required for text-conditioned motion generation. We introduce MoScale, a …
Humanoid Locomotion as Next Token Prediction
We cast real-world humanoid control as a next token prediction problem, akin to predicting the next word in language. Our model is a causal transformer trained via autoregressive prediction of sensorimotor trajectories. …
Humanoid ControlPredictionNext Patch Prediction for Autoregressive Visual Generation
Autoregressive models, built based on the Next Token Prediction (NTP) paradigm, show great potential in developing a unified framework that integrates both language and vision tasks. In this work, we rethink the NTP for …
Image GenerationPredictionNextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discret…
Text-to-Image GenerationImage Editing