CAMP: A Context-Aware, Multimodal, and Privacy-Preserving Pedestrian Trajectory Prediction Framework
Bin Yue, Shuyu Li, Anyu Liu · 2026
Read CAMP: A Context-Aware, Multimodal, and Privacy-Preserving Pedestrian Trajectory Prediction Framework by Bin Yue, Shuyu Li, Anyu Liu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13207786.txt.
Description
Bin Yue, Shuyu Li, and Anyu Liu published this study in 2026. It presents a system that predicts where a walking person will go next, a skill that robots and crowd analysts need. Recent systems gain accuracy by learning personal habits, but that creates a privacy risk.
Their system, called CAMP, reads three kinds of input: the person's path so far, the motion in the scene, and a map of costs that steers paths away from obstacles. It splits motion into shared habits and personal habits. Only the personal branch is trained with a privacy method that adds noise, so habits stay hidden. On a standard test set, the system matched strong rivals on accuracy. Its private version kept a fair balance between accuracy and privacy across several settings.
Catalog record
| CREATOR | Bin Yue, Shuyu Li, Anyu Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |