You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction

• URL: http://arxiv.org/abs/2110.05304v1
• Date: Mon, 11 Oct 2021 14:24:15 GMT
• Title: You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction
• Authors: Osama Makansi, Julius von K\"ugelgen, Francesco Locatello, Peter Gehler,Dominik Janzing, Thomas Brox and Bernhard Sch\"olkopf
• Abstract summary: Recent deep learning approaches for trajectory prediction show promising performance. It remains unclear which features such black-box models actually learn to use for making predictions. This paper proposes a procedure that quantifies the contributions of different cues to model performance.
• Score: 52.442129609979794
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Predicting the future trajectory of a moving agent can be easy when the past trajectory continues smoothly but is challenging when complex interactions with other agents are involved. Recent deep learning approaches for trajectory prediction show promising performance and partially attribute this to successful reasoning about agent-agent interactions. However, it remains unclear which features such black-box models actually learn to use for making predictions. This paper proposes a procedure that quantifies the contributions of different cues to model performance based on a variant of Shapley values. Applying this procedure to state-of-the-art trajectory prediction methods on standard benchmark datasets shows that they are, in fact, unable to reason about interactions. Instead, the past trajectory of the target is the only feature used for predicting its future. For a task with richer social interaction patterns, on the other hand, the tested models do pick up such interactions to a certain extent, as quantified by our feature attribution method. We discuss the limits of the proposed method and its links to causality

Related papers

• Enhancing Interaction Modeling with Agent Selection and Physical Coefficient for Trajectory Prediction [1.6954753390775528]
  We present ASPILin, which manually selects interacting agents and calculates their correlations instead of attention scores. Remarkably, experiments conducted on the INTERACTION, highD, and CitySim datasets demonstrate that our method is efficient and straightforward.
  arXiv  Detail & Related papers  (2024-05-21T18:45:18Z)
• MAP-Former: Multi-Agent-Pair Gaussian Joint Prediction [6.110153599741102]
  There is a gap in risk assessment of trajectories between the trajectory information coming from a traffic motion prediction module and what is actually needed. Existing prediction models yield joint predictions of agents' future trajectories with uncertainty weights or marginal Gaussian probability density functions (PDFs) for single agents. This paper introduces a novel approach to motion prediction, focusing on predicting agent-pair covariance matrices in a scene-centric'' manner.
  arXiv  Detail & Related papers  (2024-04-30T06:21:42Z)
• HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention [76.37139809114274]
  HPNet is a novel dynamic trajectory forecasting method. We propose a Historical Prediction Attention module to automatically encode the dynamic relationship between successive predictions. Our code is available at https://github.com/XiaolongTang23/HPNet.
  arXiv  Detail & Related papers  (2024-04-09T14:42:31Z)
• Certified Human Trajectory Prediction [66.1736456453465]
  Tray prediction plays an essential role in autonomous vehicles. We propose a certification approach tailored for the task of trajectory prediction. We address the inherent challenges associated with trajectory prediction, including unbounded outputs, and mutli-modality.
  arXiv  Detail & Related papers  (2024-03-20T17:41:35Z)
• Interpretable Long Term Waypoint-Based Trajectory Prediction Model [1.4778851751964937]
  We study the impact of adding a long-term goal on the performance of a trajectory prediction framework. We present an interpretable long term waypoint-driven prediction framework (WayDCM)
  arXiv  Detail & Related papers  (2023-12-11T09:10:22Z)
• Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction [27.614778027454417]
  We propose a novel approach that uses lane information to predict a future relationship among agents. To obtain a coarse future motion of agents, our method first predicts the probability of lane-level waypoint occupancy of vehicles. We then utilize the temporal probability of passing adjacent lanes for each agent pair, assuming that agents passing adjacent lanes will highly interact.
  arXiv  Detail & Related papers  (2023-05-24T04:33:28Z)
• Exploring Social Posterior Collapse in Variational Autoencoder for Interaction Modeling [26.01824780050843]
  Variational Autoencoder (VAE) has been widely applied in multi-agent interaction modeling. VAE is prone to ignoring historical social context when predicting the future trajectory of an agent. We propose a novel sparse graph attention message-passing layer, which helps us detect social posterior collapse.
  arXiv  Detail & Related papers  (2021-12-01T06:20:58Z)
• TNT: Target-driveN Trajectory Prediction [76.21200047185494]
  We develop a target-driven trajectory prediction framework for moving agents. We benchmark it on trajectory prediction of vehicles and pedestrians. We outperform state-of-the-art on Argoverse Forecasting, INTERACTION, Stanford Drone and an in-house Pedestrian-at-Intersection dataset.
  arXiv  Detail & Related papers  (2020-08-19T06:52:46Z)
• Ambiguity in Sequential Data: Predicting Uncertain Futures with Recurrent Models [110.82452096672182]
  We propose an extension of the Multiple Hypothesis Prediction (MHP) model to handle ambiguous predictions with sequential data. We also introduce a novel metric for ambiguous problems, which is better suited to account for uncertainties.
  arXiv  Detail & Related papers  (2020-03-10T09:15:42Z)
• Value-driven Hindsight Modelling [68.658900923595]
  Value estimation is a critical component of the reinforcement learning (RL) paradigm. Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function. We develop an approach for representation learning in RL that sits in between these two extremes. This provides tractable prediction targets that are directly relevant for a task, and can thus accelerate learning the value function.
  arXiv  Detail & Related papers  (2020-02-19T18:10:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.