Séminaire des équipes de recherche
A Quest for Human-Robot Cohabitation: Towards Human-Centered Autonomous Driving
- Date : 26/09/2017
- Place : Inria de Paris - 2 rue Simone Iff - Jacques-Louis Lions 2, 14h00
- Guest(s) : Mohan Manubhai Trivedi (University of California San Diego, USA)
- Organiser(s) : Fawzi Nashashibi (EP Rits)
Intelligent vehicle technology has made dramatic strides to realize large-scale deployment of self-driving automobiles on roadways in the near future. This has become possible with major advances in imaging sensors, simultaneous localization and mapping, embedded computing, and machine perception, learning, planning and control. Researchers engaged in the autonomous driving field are also realizing that many important issues need deeper examination so that the safety, reliability and robustness of these highly complex systems can be assured. In this presentation, we highlight research issues as they relate to the understanding of human agents interacting with the automated vehicle, either as occupants of such vehicles, or in the near vicinity of the vehicles. The main idea is to develop an approach to properly design, implement and evaluate methods and computational frameworks for distributed systems where intelligent robots and humans cohabit, with proper understanding of mutual goals, plans, intentions, risks and safety parameters. We emphasize the need and the implications of utilizing a holistic approach, where driving in a naturalistic context is observed over long periods to learn behaviors of human agents in order to predict intentions and interactivity patterns of all intelligent agents. Further advancements in the highly automated driving field are stimulating new research efforts in perception and semantic understanding of dynamic events, novel architectures for distributed cognitive systems, machine learning, and fail-safe system design. This presentation will give examples of some of the accomplishments in the design of such systems and also highlight important research challenges yet to be overcome.
Links to Related Papers: http://cvrr.ucsd.edu/publications/index.html