Collaborative Uncertainty in Multi-Agent Trajectory Forecasting
Dec 6, 2021
Speakers
Bohan Tang
Speaker · 0 followers
Yiqi Zhong
Speaker · 0 followers
Ulrich Neumann
Speaker · 0 followers
Siheng Chen
Speaker · 0 followers
About
Uncertainty modeling is critical in trajectory-forecasting systems for both interpretation and safety reasons. To better predict the future trajectories of multiple agents, recent works have introduced interaction modules to capture interactions among agents. This approach leads to correlations among the predicted trajectories. However, the uncertainty brought by such correlations is neglected. To fill this gap, we propose a novel concept, collaborative uncertainty (CU), which models the uncertainty resulting from the interaction module. We build a general CU-based framework to make a prediction model learn the future trajectory and the corresponding uncertainty. The CU-based framework is integrated as a plugin module to current state-of-the-art (SOTA) systems and deployed in two special cases based on multivariate Gaussian and Laplace distributions. In each case, we conduct extensive experiments on two synthetic datasets and two public, large-scale benchmarks of trajectory forecasting. The results are promising: 1) The results of synthetic datasets show that CU-based framework allows the model to nicely rebuild the ground-truth distribution. 2) The results of trajectory forecasting benchmarks demonstrate that the CU-based framework steadily helps SOTA systems improve their performances. Specially, the proposed CU-based framework helps VectorNet improve by 57 cm regarding Final Displacement Error on nuScenes dataset. 3) The visualization results of CU illustrate that CU is highly related to the interaction information provided to the model by the input data.Uncertainty modeling is critical in trajectory-forecasting systems for both interpretation and safety reasons. To better predict the future trajectories of multiple agents, recent works have introduced interaction modules to capture interactions among agents. This approach leads to correlations among the predicted trajectories. However, the uncertainty brought by such correlations is neglected. To fill this gap, we propose a novel concept, collaborative uncertainty (CU), which models the uncerta…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Pipeline Combinators for Gradual AutoML
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Zero Time Waste: Recycling Predictions in Early Exit Neural Networks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Active 3D Shape Reconstruction from Vision and Touch
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network
Watch later
Xiaolin Hu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Unsupervised Domain Adaptation with Adapter
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
ELLA: Exploration through Learned Language Abstraction
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%