pith. sign in

arxiv: 1706.05904 · v2 · pith:GMCK4MLYnew · submitted 2017-06-19 · 💻 cs.CV

Pedestrian Prediction by Planning using Deep Neural Networks

classification 💻 cs.CV
keywords planningpredictiondestinationsmotionneuralpredictsystemability
0
0 comments X
read the original abstract

Accurate traffic participant prediction is the prerequisite for collision avoidance of autonomous vehicles. In this work, we predict pedestrians by emulating their own motion planning. From online observations, we infer a mixture density function for possible destinations. We use this result as the goal states of a planning stage that performs motion prediction based on common behavior patterns. The entire system is modeled as one monolithic neural network and trained via inverse reinforcement learning. Experimental validation on real world data shows the system's ability to predict both, destinations and trajectories accurately.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.