Identifying Driver Interactions via Conditional Behavior Prediction

by   Ekaterina Tolstaya, et al.
University of Pennsylvania

Interactive driving scenarios, such as lane changes, merges and unprotected turns, are some of the most challenging situations for autonomous driving. Planning in interactive scenarios requires accurately modeling the reactions of other agents to different future actions of the ego agent. We develop end-to-end models for conditional behavior prediction (CBP) that take as an input a query future trajectory for an ego-agent, and predict distributions over future trajectories for other agents conditioned on the query. Leveraging such a model, we develop a general-purpose agent interactivity score derived from probabilistic first principles. The interactivity score allows us to find interesting interactive scenarios for training and evaluating behavior prediction models. We further demonstrate that the proposed score is effective for agent prioritization under computational budget constraints.


page 1

page 2

page 3

page 4


ProspectNet: Weighted Conditional Attention for Future Interaction Modeling in Behavior Prediction

Behavior prediction plays an important role in integrated autonomous dri...

Interventional Behavior Prediction: Avoiding Overly Confident Anticipation in Interactive Prediction

Conditional behavior prediction (CBP) builds up the foundation for a coh...

Contingencies from Observations: Tractable Contingency Planning with Learned Behavior Models

Humans have a remarkable ability to make decisions by accurately reasoni...

Introducing Risk Shadowing For Decisive and Comfortable Behavior Planning

We consider the problem of group interactions in urban driving. State-of...

BiFF: Bi-level Future Fusion with Polyline-based Coordinate for Interactive Trajectory Prediction

Predicting future trajectories of surrounding agents is essential for sa...

Generic Probabilistic Interactive Situation Recognition and Prediction: From Virtual to Real

Accurate and robust recognition and prediction of traffic situation play...

Domain Knowledge Driven Pseudo Labels for Interpretable Goal-Conditioned Interactive Trajectory Prediction

Motion forecasting in highly interactive scenarios is a challenging prob...

Please sign up or login with your details

Forgot password? Click here to reset