SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction
원문 초록
We propose advances that address two key challenges in future trajectory prediction: (i) multimodality in both training data and predictions and (ii) constant time inference regardless of number of agents. Existing trajectory predictions are fundamentally limited by lack of diversity in training data, which is difficult to acquire with sufficient coverage of possible modes. Our first contribution is an automatic method to simulate diverse trajectories in the top-view. It uses pre-existing datasets and maps as initialization, mines existing trajectories to represent realistic driving behaviors and uses a multi-agent vehicle dynamics simulator to generate diverse new trajectories that cover various modes and are consistent with scene layout constraints. Our second contribution is a novel method that generates diverse predictions while accounting for scene semantics and multi-agent interactions, with constant-time inference independent of the number of agents. We propose a convLSTM with novel state pooling operations and losses to predict scene-consistent states of multiple agents in a single forward pass, along with a CVAE for diversity. We validate our proposed multi-agent trajectory prediction approach by training and testing on the proposed simulated dataset and existing real datasets of traffic scenes. In both cases, our approach outperforms SOTA methods by a large margin, highlighting the benefits of both our diverse dataset simulation and constant-time diverse trajectory prediction methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory Prediction
Egocentric Event-Based Vision for Ping Pong Ball Trajectory Prediction
Multi-Strategy Improved Snake Optimizer Accelerated CNN-LSTM-Attention-Adaboost for Trajectory Prediction
ILNet: Trajectory Prediction with Inverse Learning Attention for Enhancing Intention Capture
M2BeamLLM: Multimodal Sensing-empowered mmWave Beam Prediction with Large Language Models
Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Review
토론
이 논문과 연결된 포럼 글이 아직 없습니다.