[robotics-worldwide] [jobs] Doctoral Research Position on "Governing automated vehicle behavior"

Raja Chatila raja.chatila at isir.upmc.fr
Tue Nov 8 02:09:28 PST 2016


• Title : Governing automated vehicle behavior 
• Contract duration: 36 months 
• Funding: AVEthics project (ANR - French National research Agency) & VEDECOM* Institute  
• Application: as soon as possible 
• PhD Supervisor : Raja Chatila - raja.chatila at isir.upmc.fr 
• VEDECOM supervisor :  Ebru Dogan  - ebru.dogan at vedecom.fr 
• Academic partner: Institute for Intelligent Systems and Robotics (ISIR), Université Pierre et Marie Curie (UPMC) 
• Industrial partners: Renault S. A. & PSA Peugeot Citroën 
• Location: Université Pierre et Marie Curie (UPMC), Paris and VEDECOM* Institute , Versailles.

Deadline: November 30, 2016 (Please note that an FCFS policy will be
followed in the evaluation of the applications until a suitable candidate
is appointed.)

Automated vehicles (AVs) will soon share roads and streets with other users and vehicles – automated or not – and in crowded urban environment, with pedestrians, cyclists and other mobile objects. The AV decision-making system will have to cope not only with actual traffic conditions, abide by traffic rules, stop on traffic lights, yield to traffic with higher priority, etc. but also avoid obstacles and correctly react in unusual and unpredicted situations, such as pedestrians suddenly crossing the street or other vehicles abnormal motions. When all vehicles will be automated and connected, such situations will tend to decrease, but deployment of AVs will probably be gradual, and there will remain pedestrians on the streets. It is therefore of prime importance that the AVs is equipped with a decision-making system that enables it to manage its driving at all times and in all situations. 

This thesis proposal is in the framework of the ANR AVEthics project, “Ethics policy for automated vehicle”, granted to VEDECOM Institute, the Institute of Intelligent Systems and Robotics (ISIR) at University Pierre and Marie Curie, and University Paris-Sorbonne. The focus is the ethical conduct of an automated vehicle during its driving in usual conditions, but also when facing situations wherein it must take decisions involving ethical choices (Greenblatt, 2016), i.e., decisions that all have negative consequences, but that have nevertheless to be made. 

The objective of the current thesis to conduct research in Robotics and Artificial Intelligence to design and validate a decision-making system, which will be used as a research tool to model the properties of an artificial ethics in order to test the interactions of an AV with other road users in dilemma situations. 
There are several moral theories that try to explain or to guide human decisions (deontic, utilitarian, casuistic …) that could be applied as such to machine decisions. One of the first tasks of the candidate will be to study moral theories and to become acquainted with their philosophical foundations. Simultaneously, literature on machine ethics will be also studied (Allen 2006, Chauvier 2014), specifically in the context of autonomous vehicles (Lin 2015, Bonnefon 2015). An artificial moral agent implementing different moral theories as well as casuistic and pragmatic approaches will be then developed and implemented (McLaren 2006). Driving is typically in uncertain and evolving conditions. Not only perception and interpretation of situations is uncertain, but also actions are not deterministic and their consequences cannot be predicted exactly due for example to vehicle motion (e.g., skidding) or other vehicle reactions. Research will therefore explore and implement uncertain representations, e.g., Bayesian representations and Bayesian networks (Ferreira 2013) and decision-making approaches, e.g., Markov processes or game theory, in the context of multi-agent systems, in which each agent have partial information, non-identical and maybe conflicting goals and interests, as well as different computational capacities. This is a major objective of the thesis. 
The work will also include the development of a simulation environment to study scenarios and situations for characterizing different ethical approaches, and enabling to study human reactions as well. Furthermore, the work will investigate how the system could be able to adapt its behavior by learning from user decisions, instead of merely applying its own policy. The simulation environment will have to embed this capacity. Research will be performed to propose an appropriate learning approach from acquired data on the situation and driver decisions (Droniou 2014, Sutton 1998). This will also enable to provide a comparative study on human and artificial ethics. 

• Master in Computer Science or Electrical Engineering, 
• Background in Robotics, Perception, Probabilistic and Bayesian reasoning
• Strong programming skills (C, C++, other). 
• Experience in serious games and simulation environments is a plus. 
• Languages: English, French

To apply please send to Raja Chatila (raja.chatila at isir.upmc.fr <mailto:raja.chatila at isir.upmc.fr>) and Ebru Dogan (ebru.dogan at vedecom.fr <mailto:ebru.dogan at vedecom.fr>):

1- Detailed CV
2- Short motivation letter describing your research interests and background.
Please include the name and contact information of at least one person reference person.

Thank you.

*VEDECOM: Institut du Véhicule Décarboné Communicant et sa Mobilité - https://urldefense.proofpoint.com/v2/url?u=http-3A__www.vedecom.fr&d=DgIFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=pRDWYhK6S2bUo2wH-RJf0pydo5GVVZSXU-OhEDEvJfY&s=KlWSrTD46zA-2KzrhU5vXJT9AoxO6MT5UKYMqOFXL68&e= 
VeDeCoM is a French "institute for energy transition". It is supported by the Mov’eo competitiveness cluster, and by community organisations. It's located in Versailles, South West of Paris.The aim of VeDeCoM is to foster research and innovation on pre-competitive and pre-normative topics in a public-private partnership along three domains : 1) new electric vehicle powertrains, 2) driving delegation, and autonomous and connected vehicles, 3) shared mobility and energy based on new usages and innovative infrastructures and services. VeDeCoM involves more than 40 industrial and academic members. Its staff gathers scientist and engineers in physics and chemistry, mechanical and electrical engineering, information and communication, telecommunication, psychology, sociology and economy to explore new use cases.

More information about the robotics-worldwide mailing list