Multi-Agent Trajectory Prediction With Heterogeneous Edge-Enhanced Graph Attention Network

Abstract

Simultaneous trajectory prediction for multiple heterogeneous traffic participants is essential for safe and efficient operation of connected automated vehicles under complex driving situations. Two main challenges for this task are to handle the varying number of heterogeneous target agents and jointly consider multiple factors that would affect their future motions. This is because different kinds of agents have different motion patterns, and their behaviors are jointly affected by their individual dynamics, their interactions with surrounding agents, as well as the traffic infrastructures. A trajectory prediction method handling these challenges will benefit the downstream decisionmaking and planning modules of autonomous vehicles.To meet these challenges, we propose a three-channel framework together with a novel Heterogeneous Edge-enhanced graph ATtention network (HEAT). Our framework is able to deal with the heterogeneity of the target agents and traffic participants involved. Specifically, agents' dynamics are extracted from their historical states using type-specific encoders. The inter-agent interactions are represented with a directed edgefeatured heterogeneous graph and processed by the designed HEAT network to extract interaction features. Besides, the map features are shared across all agents by introducing a selective gate-mechanism. And finally, the trajectories of multiple agents are predicted simultaneously. Validations using both urban and highway driving datasets show that the proposed model can realize simultaneous trajectory predictions for multiple agents under complex traffic situations, and achieve state-of-the-art performance with respect to prediction accuracy. The achieved final displacement error (FDE@3sec) is 0.66 meter under urban driving, demonstrating the feasibility and effectiveness of the proposed approach.

M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction

“…For a fair comparison, we use the numbers reported on the official benchmark website [1] and only include the published models. Similar to the observations from the validation set, we observe that M2I improves mAP metrics by a large margin, compared to past WOMD interaction prediction challenge winners [27,38] and the existing state-of-the-art model [28].…”

“…HeatIRm4 [27] models the agent interaction as a directed edge feature graph and leverages an attention network to extract interaction features. It was the winner of the 2021 WOMD challenge.…”

Human–Machine Telecollaboration Accelerates the Safe Deployment of Large-Scale Autonomous Robots During the COVID-19 Pandemic

“…Therefore, interaction awareness and forecasting are important for safe robot operations. Recently, we proposed a novel deep learning model that uses only one second of historical data to accurately predict the robot motion and its interactions with surrounding agents up to 8 s ahead, wining the first Place of Interaction Prediction Track at 2021 Waymo Open Dataset Challenges ( Mo et al, 2022 ). The visualized interaction prediction results effectively help operators understand the situation and make safe decisions.…”

D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights

“…LB-EBM [30] is a probabilistic model with cost function defined in the latent space to account for the movement history and social context for diverse human trajectories. HEAT [28], TNT [18], and MultiPath [51] are used on INTERAC-TION and reported in [18].…”