# Learning Velocity and Acceleration: Self-Supervised Motion Consistency for Pedestrian Trajectory Prediction

arXiv: https://arxiv.org/abs/2503.24272 · HTML: https://mlsanity.com/paper/2503.24272/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Builds on (most cited first, 19 of 19)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting](https://mlsanity.com/paper/2103.14023/) (2021)
- [It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction](https://mlsanity.com/paper/2004.02025/) (2020)
- [Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion](https://mlsanity.com/paper/2203.13777/) (2022)
- [From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting](https://mlsanity.com/paper/2012.01526/) (2020)
- [Remember Intentions: Retrospective-Memory-based Trajectory Prediction](https://mlsanity.com/paper/2203.11474/) (2022)
- [Human Trajectory Prediction via Neural Social Physics](https://mlsanity.com/paper/2207.10435/) (2022)
- [LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints](https://mlsanity.com/paper/2302.13933/) (2023)
- [Interpretable Social Anchors for Human Trajectory Forecasting in Crowds](https://mlsanity.com/paper/2105.03136/) (2021)
- [EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting](https://mlsanity.com/paper/2307.09306/) (2023)
- [SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2310.05370/) (2023)
- [MSN: Multi-Style Network for Trajectory Prediction](https://mlsanity.com/paper/2107.00932/) (2021)
- [Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSM](https://mlsanity.com/paper/2503.10898/) (2025)
- [What Do You See in Vehicle? Comprehensive Vision Solution for In-Vehicle Gaze Estimation](https://mlsanity.com/paper/2403.15664/) (2024)
- [A Novel Benchmarking Paradigm and a Scale- and Motion-Aware Model for Egocentric Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2310.10424/) (2023)
- [Evaluating Pedestrian Trajectory Prediction Methods with Respect to Autonomous Driving](https://mlsanity.com/paper/2308.05194/) (2023)
- [Human-Robot Gym: Benchmarking Reinforcement Learning in Human-Robot Collaboration](https://mlsanity.com/paper/2310.06208/) (2023)
- [Social Motion Prediction with Cognitive Hierarchies](https://mlsanity.com/paper/2311.04726/) (2023)
- [Attention-aware Social Graph Transformer Networks for Stochastic Trajectory Prediction](https://mlsanity.com/paper/2312.15881/) (2023)

## Built on by (most cited first, 1 of 1)

- [Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Review](https://mlsanity.com/paper/2506.14831/) (2025)

## Abstract (arXiv)

Understanding human motion is crucial for accurate pedestrian trajectory prediction. Conventional methods typically rely on supervised learning, where ground-truth labels are directly optimized against predicted trajectories. This amplifies the limitations caused by long-tailed data distributions, making it difficult for the model to capture abnormal behaviors. In this work, we propose a self-supervised pedestrian trajectory prediction framework that explicitly models position, velocity, and acceleration. We leverage velocity and acceleration information to enhance position prediction through feature injection and a self-supervised motion consistency mechanism. Our model hierarchically injects velocity features into the position stream. Acceleration features are injected into the velocity stream. This enables the model to predict position, velocity, and acceleration jointly. From the predicted position, we compute corresponding pseudo velocity and acceleration, allowing the model to learn from data-generated pseudo labels and thus achieve self-supervised learning. We further design a motion consistency evaluation strategy grounded in physical principles; it selects the most reasonable predicted motion trend by comparing it with historical dynamics and uses this trend to guide and constrain trajectory generation. We conduct experiments on the ETH-UCY and Stanford Drone datasets, demonstrating that our method achieves state-of-the-art performance on both datasets.