Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction
Multi-agent interactions are important to model for forecasting other agents' behaviors and trajectories. At a certain time, to forecast a reasonable future trajectory, each agent needs to pay attention to the interactions with only a small group of most relevant agents instead of unnecessarily paying attention to all the other agents. However, existing attention modeling works ignore that human attention in driving does not change rapidly, and may introduce fluctuating attention across time steps. In this paper, we formulate an attention model for multi-agent interactions based on a total variation temporal smoothness prior and propose a trajectory prediction architecture that leverages the knowledge of these attended interactions. We demonstrate how the total variation attention prior along with the new sequence prediction loss terms leads to smoother attention and more sample-efficient learning of multi-agent trajectory prediction, and show its advantages in terms of prediction accuracy by comparing it with the state-of-the-art approaches on both synthetic and naturalistic driving data. We demonstrate the performance of our algorithm for trajectory prediction on the INTERACTION dataset on our website.
Code (0)
등록된 구현이 없습니다.
Tasks
PredictionTrajectory PredictionSimilar Papers 제목 키워드 기반
Learning to Focus: Prioritizing Informative Histories with Structured Attention Mechanisms in Partially Observable Reinforcement Learning
Transformers have shown strong ability to model long-term dependencies and are increasingly adopted as world models in model-based reinforcement learning (RL) under partial observability. However, unlike natural language…
Reinforcement LearningGNNRL-Smoothing: A Prior-Free Reinforcement Learning Model for Mesh Smoothing
Mesh smoothing methods can enhance mesh quality by eliminating distorted elements, leading to improved convergence in simulations. To balance the efficiency and robustness of traditional mesh smoothing process, previous …
reinforcement-learningReinforcement LearningVariance-Penalized MC-Dropout as a Learned Smoothing Prior for Brain Tumour Segmentation
Brain tumor segmentation is essential for diagnosis and treatment planning, yet many CNN and U-Net based approaches produce noisy boundaries in regions of tumor infiltration. We introduce UAMSA-UNet, an Uncertainty-Aware…
Computational EfficiencyBrain Tumor SegmentationSmooth-Trajectron++: Augmenting the Trajectron++ behaviour prediction model with smooth attention
Understanding traffic participants' behaviour is crucial for predicting their future trajectories, aiding in developing safe and reliable planning systems for autonomous vehicles. Integrating cognitive processes and mach…
Autonomous DrivingAutonomous VehiclesTrajectory ForecastingTrajectory PredictionPi-transformer: A prior-informed dual-attention model for multivariate time-series anomaly detection
Anomalies in multivariate time series often arise from temporal context and cross-channel coordination rather than isolated outliers. We present Pi-Transformer (Prior-Informed Transformer), a transformer with two attenti…
Anomaly Detection