Multimodal Trajectory Prediction
Overview
Multimodal trajectory prediction studies how to forecast multiple plausible future paths when an agent’s intent or interactions are uncertain, in settings from road traffic and crowds to vessels and robots. Methods include CVAEs, GANs, Gaussian mixtures, diffusion and flow models, motion-prior retrieval, and Transformer or state-space architectures that use histories, maps, images, and social interactions. They are evaluated on benchmarks such as Waymo, Argoverse, nuScenes, and ETH/UCY, with growing attention to probability calibration, physical feasibility, and joint consistency among agents. A central tension is producing diverse, well-ranked forecasts that remain safe and useful in closed-loop planning without excessive inference cost.
Latest papers
56 papers11 papers in the last four weeks, up 57% on the four weeks before. 0.1% of all new papers.