Advertisement

A Reinforcement Learning Approach for Designing and Optimizing Interaction Strategies for a Human–Machine Interface of a PADAS

  • Fabio Tango
  • Maria Alonso
  • M. Henar Vega
  • Raghav Aras
  • Olivier Pietquin
Conference paper

Abstract

The FP7 EU project ISi-PADAS (Integrated Human Modelling and Simulation to support Human Error Risk Analysis of Partially Autonomous Driver Assistance Systems) endeavours to conceive an intelligent system called PADAS (Partially Autonomous Driver Assistance System) for aiding human drivers in driving safely by providing them with pertinent and accurate information in real time about the external situation and by acting as a co-pilot in emergency conditions. The system interacts with the driver through a Human–Machine Interface (HMI) installed on the vehicle using an adequate Warning and Intervention Strategy (WIS). In this paper, the design of the PADAS HMI as well as a decision-theoretic approach for deriving an optimal WIS are described.

Keywords

Human machine interface Decision making support systems Machine learning / reinforcement learning Partially autonomous driving assistance systems Optimal strategies 

Notes

Acknowledgment

The research leading to these results has received funding from the European Commission Seventh Framework Programme (FP7/2007–2013) under grant agreement no. FP7-218552, Project ISi-PADAS (Integrated Human Modelling and Simulation to support Human Error Risk Analysis of Partially Autonomous Driver Assistance Systems). The authors would like to specially thank the ISi-PADAS consortium that has supported the development of this research.

References

  1. 1.
    Alsen J et al (2010) Integrated human modelling and simulation to support Human Error Risk Analysis of Partially Autonomous Driver Assistance Systems: the ISI-PADAS Project. Transport Research Arena Europe, Brussels 2010Google Scholar
  2. 2.
    ISO Standard 13407 (1999) Human-Centered design processes for interactive systems. Reference number ISO 13407:1999(E), Technical Committee ISO/TC 159, Ergonomics, Subcommittee SC 4, Ergonomics of human-system interactionGoogle Scholar
  3. 3.
    ISO Standard 9241-11 (1998) Ergonomic requirements for office work with visual display terminals (VDTs)—Part 11: Guidance on usabilityGoogle Scholar
  4. 4.
    ISO Standard ISO/FDIS 15623 (2001) Road vehicles—Forward Vehicle Collision Warning System—Performance requirements and test procedures. Reference number of working document: ISO/TC 204/WG 14 N 144.19, Reference number of document: ISO/FDIS 15623, Committee identification: ISO/TC 204/WG 14Google Scholar
  5. 5.
    ISO Standard ISO/PWI 15662 (2007) Road vehicles—Adaptive Cruise Control Systems—Performance requirements and test procedures. Reference number of working document: ISO/TC 204/WG 14 N 457.3, Reference number of document: ISO/PWI 15662, Committee identification: ISO/TC 204/WG 14Google Scholar
  6. 6.
    Michon JA (1985) A critical view of driver behaviour models: What do we know, what should we do? In: Evans L, Schwing RC (eds) Human Behaviour and Traffic Safety. Plenum, New YorkGoogle Scholar
  7. 7.
    Puterman ML (1994) Markov decision processes: discrete stochastic dynamic programming. Wiley, New YorkGoogle Scholar

Copyright information

© Springer-Verlag Italia Srl 2011

Authors and Affiliations

  • Fabio Tango
    • 1
  • Maria Alonso
    • 2
  • M. Henar Vega
    • 2
  • Raghav Aras
    • 3
  • Olivier Pietquin
    • 3
  1. 1.CRF−Centro Ricerche FiatOrbassanoItaly
  2. 2.CIDAUT Foundation, Parque Tecnológico de BoecilloValladolidSpain
  3. 3.SUPELECMetzFrance

Personalised recommendations