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

62 papers3 papers in the last four weeks, down 75% on the four weeks before. 0.0% of all new papers.

Oct 12, 2025

Controllable Generative Trajectory Prediction via Weak Preference Alignment

Deep generative models such as conditional variational autoencoders (CVAEs) have shown great promise for predicting trajectories of surrounding agents in autonomous vehicle planning. State-of-the-art models have achieved remarkable accuracy in such prediction tasks. Besides accuracy, diversity is also crucial for safe planning because human behaviors are inherently uncertain and multimodal. However, existing methods generally lack a scheme to generate controllably diverse trajectories, which is arguably more useful than randomly diversified trajectories, to the end of safe planning. To address this, we propose PrefCVAE, an augmented CVAE framework that uses weakly labeled preference pairs to imbue latent variables with semantic attributes. Using average velocity as an example attribute, we demonstrate that PrefCVAE enables controllable, semantically meaningful predictions without degrading baseline accuracy. Our results show the effectiveness of preference supervision as a cost-effective way to enhance sampling-based generative models.
Sep 12, 2025

BEVTraj: Map-Free Multimodal Trajectory Prediction with Sensor-Derived BEV Context and Sparse Goal Reasoning

Trajectory prediction is a key task in autonomous driving, where a model must forecast plausible future motions of surrounding agents from dynamic histories and scene context. Many recent methods use high-definition (HD) maps to provide explicit road topology and semantic constraints, but such maps are costly to maintain, geographically limited, and difficult to update in changing environments. This paper presents Bird's-Eye View Trajectory Prediction (BEVTraj), a map-free trajectory prediction framework that directly uses BEV features constructed from raw multi-sensor data. Since sensor-derived BEV features are dense and only implicitly structured, BEVTraj employs deformable attention to selectively aggregate agent-relevant spatial context from sparse locations rather than processing the entire BEV grid uniformly. In addition, a Sparse Goal Candidate Proposal module combines overlapping mode-wise anchor clusters with attention-based goal prediction to generate compact, scene-adaptive goal hypotheses. These goals are decoded and iteratively refined into multimodal trajectories, while trajectory-aware mode scoring and temporal consistency modeling improve confidence estimation and suppress abrupt, physically implausible refinement updates. Experiments on nuScenes and Argoverse 2 Sensor show that BEVTraj achieves competitive results under a map-free setting without using pre-built HD maps, while ablation studies and qualitative analyses illustrate the roles of BEV context aggregation and sparse goal reasoning. The source code is available at https://github.com/Kongminsang/bevtraj.