DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents

We introduce a Deep Stochastic IOC RNN Encoderdecoder framework, DESIRE, for the task of future predictions of multiple interacting agents in dynamic scenes. DESIRE effectively predicts future locations of objects in multiple scenes by 1) accounting for the multi-modal nature of the future prediction (i.e., given the same context, future may vary), 2) foreseeing the potential future outcomes and make a strategic prediction based on that, and 3) reasoning not only from the past motion history, but also from the scene context as well as the interactions among the agents. DESIRE achieves these in a single end-to-end trainable neural network model, while being computationally efficient. The model first obtains a diverse set of hypothetical future prediction samples employing a conditional variational autoencoder, which are ranked and refined by the following RNN scoring-regression module. Samples are scored by accounting for accumulated future rewards, which enables better long-term strategic decisions similar to IOC frameworks. An RNN scene context fusion module jointly captures past motion histories, the semantic scene context and interactions among multiple agents. A feedback mechanism iterates over the ranking and refinement to further boost the prediction accuracy. We evaluate our model on two publicly available datasets: KITTI and Stanford Drone Dataset. Our experiments show that the proposed model significantly improves the prediction accuracy compared to other baseline methods.

PDF Abstract CVPR 2017 PDF CVPR 2017 Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Trajectory Prediction INTERACTION Dataset - Validation DESIRE minADE6 0.32 # 3
minFDE6 0.88 # 4
Multi Future Trajectory Prediction KITTI-trajectory-prediction DESIRE ADE@4s (K=5) - # 3
FDE@4s (K=5) 2.06 # 1
FDE@4s (K=20) 2.04 # 2
Trajectory Prediction PAID DESIRE minFDE3 0.59 # 1
minADE3 0.29 # 1

Results from Other Papers

Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Trajectory Prediction Stanford Drone DESIRE ADE-8/12 @K = 20 19.25 # 15
FDE-8/12 @K= 20 34.05 # 15
ADE (8/12) @K=5 19.25 # 3
FDE(8/12) @K=5 34.05 # 3


No methods listed for this paper. Add relevant methods here