Online Residual Learning from Offline Experts for Pedestrian Tracking
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916386049097728 |
|---|---|
| author | Vlachos, Anastasios Tsiamis, Anastasios Karapetyan, Aren Balta, Efe C. Lygeros, John |
| author_facet | Vlachos, Anastasios Tsiamis, Anastasios Karapetyan, Aren Balta, Efe C. Lygeros, John |
| contents | In this paper, we consider the problem of predicting unknown targets from data. We propose Online Residual Learning (ORL), a method that combines online adaptation with offline-trained predictions. At a lower level, we employ multiple offline predictions generated before or at the beginning of the prediction horizon. We augment every offline prediction by learning their respective residual error concerning the true target state online, using the recursive least squares algorithm. At a higher level, we treat the augmented lower-level predictors as experts, adopting the Prediction with Expert Advice framework. We utilize an adaptive softmax weighting scheme to form an aggregate prediction and provide guarantees for ORL in terms of regret. We employ ORL to boost performance in the setting of online pedestrian trajectory prediction. Based on data from the Stanford Drone Dataset, we show that ORL can demonstrate best-of-both-worlds performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_04069 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Online Residual Learning from Offline Experts for Pedestrian Tracking Vlachos, Anastasios Tsiamis, Anastasios Karapetyan, Aren Balta, Efe C. Lygeros, John Systems and Control Machine Learning Optimization and Control In this paper, we consider the problem of predicting unknown targets from data. We propose Online Residual Learning (ORL), a method that combines online adaptation with offline-trained predictions. At a lower level, we employ multiple offline predictions generated before or at the beginning of the prediction horizon. We augment every offline prediction by learning their respective residual error concerning the true target state online, using the recursive least squares algorithm. At a higher level, we treat the augmented lower-level predictors as experts, adopting the Prediction with Expert Advice framework. We utilize an adaptive softmax weighting scheme to form an aggregate prediction and provide guarantees for ORL in terms of regret. We employ ORL to boost performance in the setting of online pedestrian trajectory prediction. Based on data from the Stanford Drone Dataset, we show that ORL can demonstrate best-of-both-worlds performance. |
| title | Online Residual Learning from Offline Experts for Pedestrian Tracking |
| topic | Systems and Control Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2409.04069 |