# What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction

arXiv: https://arxiv.org/abs/1903.07933 · HTML: https://mlsanity.com/paper/1903.07933/

## Key facts

- Cited by 80 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2019.

## Built on by (most cited first, 30 of 80)

- [Parting with Misconceptions about Learning-based Vehicle Motion Planning](https://mlsanity.com/paper/2306.07962/) (2023)
- [SocialVAE: Human Trajectory Prediction using Timewise Latents](https://mlsanity.com/paper/2203.08207/) (2022)
- [How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting](https://mlsanity.com/paper/2203.04781/) (2022)
- [Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approaches](https://mlsanity.com/paper/2111.06740/) (2021)
- [Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction](https://mlsanity.com/paper/2204.11561/) (2022)
- [Roto-translated Local Coordinate Frames For Interacting Dynamical Systems](https://mlsanity.com/paper/2110.14961/) (2021)
- [FloMo: Tractable Motion Prediction with Normalizing Flows](https://mlsanity.com/paper/2103.03614/) (2021)
- [CRAT-Pred: Vehicle Trajectory Prediction with Crystal Graph Convolutional Neural Networks and Multi-Head Self-Attention](https://mlsanity.com/paper/2202.04488/) (2022)
- [Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty](https://mlsanity.com/paper/2104.12446/) (2021)
- [Injecting Knowledge in Data-driven Vehicle Trajectory Predictors](https://mlsanity.com/paper/2103.04854/) (2021)
- [What Truly Matters in Trajectory Prediction for Autonomous Driving?](https://mlsanity.com/paper/2306.15136/) (2023)
- [The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation](https://mlsanity.com/paper/2504.08654/) (2025)
- [Anomaly Detection in Multi-Agent Trajectories for Automated Driving](https://mlsanity.com/paper/2110.07922/) (2021)
- [Trajectory Prediction with Linguistic Representations](https://mlsanity.com/paper/2110.09741/) (2021)
- [TrackFlow: Multi-Object Tracking with Normalizing Flows](https://mlsanity.com/paper/2308.11513/) (2023)
- [Learning Interaction-Aware Trajectory Predictions for Decentralized Multi-Robot Motion Planning in Dynamic Environments](https://mlsanity.com/paper/2102.05382/) (2021)
- [Safety-compliant Generative Adversarial Networks for Human Trajectory Forecasting](https://mlsanity.com/paper/2209.12243/) (2022)
- [RAP: Risk-Aware Prediction for Robust Planning](https://mlsanity.com/paper/2210.01368/) (2022)
- [Evaluating Pedestrian Trajectory Prediction Methods with Respect to Autonomous Driving](https://mlsanity.com/paper/2308.05194/) (2023)
- [SICNav-Diffusion: Safe and Interactive Crowd Navigation with Diffusion Trajectory Predictions](https://mlsanity.com/paper/2503.08858/) (2025)
- [Energy-based Potential Games for Joint Motion Forecasting and Control](https://mlsanity.com/paper/2312.01811/) (2023)
- [SoNIC: Safe Social Navigation with Adaptive Conformal Inference and Constrained Reinforcement Learning](https://mlsanity.com/paper/2407.17460/) (2024)
- [Under the Hood of Transformer Networks for Trajectory Forecasting](https://mlsanity.com/paper/2203.11878/) (2022)
- [Vision-based Multi-future Trajectory Prediction: A Survey](https://mlsanity.com/paper/2302.10463/) (2023)
- [EMAG: Ego-motion Aware and Generalizable 2D Hand Forecasting from Egocentric Videos](https://mlsanity.com/paper/2405.20030/) (2024)
- [Motion Forecasting for Autonomous Vehicles: A Survey](https://mlsanity.com/paper/2502.08664/) (2025)
- [Towards Robust Human Trajectory Prediction in Raw Videos](https://mlsanity.com/paper/2108.08259/) (2021)
- [Asymmetrical Bi-RNN for pedestrian trajectory encoding](https://mlsanity.com/paper/2106.04419/) (2021)
- [Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowds](https://mlsanity.com/paper/2405.16439/) (2024)
- [Towards Generalizable Safety in Crowd Navigation via Conformal Uncertainty Handling](https://mlsanity.com/paper/2508.05634/) (2025)

## Abstract (arXiv)

Pedestrian motion prediction is a fundamental task for autonomous robots and vehicles to operate safely. In recent years many complex approaches based on neural networks have been proposed to address this problem. In this work we show that - surprisingly - a simple Constant Velocity Model can outperform even state-of-the-art neural models. This indicates that either neural networks are not able to make use of the additional information they are provided with, or that this information is not as relevant as commonly believed. Therefore, we analyze how neural networks process their input and how it impacts their predictions. Our analysis reveals pitfalls in training neural networks for pedestrian motion prediction and clarifies false assumptions about the problem itself. In particular, neural networks implicitly learn environmental priors that negatively impact their generalization capability, the motion history of pedestrians is irrelevant and interactions are too complex to predict. Our work shows how neural networks for pedestrian motion prediction can be thoroughly evaluated and our results indicate which research directions for neural motion prediction are promising in future.