DiPA: Diverse and Probabilistically Accurate Interactive Prediction

by   Anthony Knittel, et al.

Accurate prediction is important for operating an autonomous vehicle in interactive scenarios. Previous interactive predictors have used closest-mode evaluations, which test if one of a set of predictions covers the ground-truth, but not if additional unlikely predictions are made. The presence of unlikely predictions can interfere with planning, by indicating conflict with the ego plan when it is not likely to occur. Closest-mode evaluations are not sufficient for showing a predictor is useful, an effective predictor also needs to accurately estimate mode probabilities, and to be evaluated using probabilistic measures. These two evaluation approaches, eg. predicted-mode RMS and minADE/FDE, are analogous to precision and recall in binary classification, and there is a challenging trade-off between prediction strategies for each. We present DiPA, a method for producing diverse predictions while also capturing accurate probabilistic estimates. DiPA uses a flexible representation that captures interactions in widely varying road topologies, and uses a novel training regime for a Gaussian Mixture Model that supports diversity of predicted modes, along with accurate spatial distribution and mode probability estimates. DiPA achieves state-of-the-art performance on INTERACTION and NGSIM, and improves over a baseline (MFP) when both closest-mode and probabilistic evaluations are used at the same time.


page 1

page 3

page 7


GAME-UP: Game-Aware Mode Enumeration and Understanding for Trajectory Prediction

Interactions between road agents present a significant challenge in traj...

P4P: Conflict-Aware Motion Prediction for Planning in Autonomous Driving

Motion prediction is crucial in enabling safe motion planning for autono...

Towards a Fatality-Aware Benchmark of Probabilistic Reaction Prediction in Highly Interactive Driving Scenarios

Autonomous vehicles should be able to generate accurate probabilistic pr...

Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction

Future prediction is a fundamental principle of intelligence that helps ...

Uncertainty estimation of pedestrian future trajectory using Bayesian approximation

Past research on pedestrian trajectory forecasting mainly focused on det...

Novel Techniques to Assess Predictive Systems and Reduce Their Alarm Burden

The performance of a binary classifier ("predictor") depends heavily upo...

Please sign up or login with your details

Forgot password? Click here to reset