Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Modeling Preemptive Behaviors for Uncommon Hazardous Situations From Demonstrations
Priyam Parashar, Akansel Cosgun, Alireza Nakhaei and Kikuo Fujimura
Oct 31, 2017 (modified: Oct 31, 2017)NIPS 2017 Workshop MLITS Submissionreaders: everyone
Abstract:This paper presents a learning from demonstration approach to programming safe, autonomous behaviors for uncommon driving scenarios. Simulation is used to re-create a targeted driving situation, one containing a road-side hazard creating significant occlusion in an urban neighborhood, and collect optimal driving behaviors from 24 users. Paper employs a key-frame based approach combined with an algorithm to linearly combine models in order to extend the behavior to novel variations of the target situation. This approach is theoretically agnostic to the kind of LfD framework used for modeling data
and our results suggest it generalizes well to variations containing additional number of hazards occurring in sequence. The linear combination algorithm is informed by analysis of driving data, which also suggests that decision making algorithms need to consider a trade-off between road-rules and immediate rewards to tackle some complex cases.
Keywords:learning from demonstration, safety planning, simulation
Enter your feedback below and we'll get back to you as soon as possible.