Robot drivers: Learning to drive by trial & error

Michael Bosello, Rita Tse, Giovanni Pau

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

Autonomous cars have been in the making for over 15 years. Skepticism has taken the place of initial hype and enthusiasm. Current autonomous driving systems give no guarantee of 100% correctness and reliability, and users are not willing to take a chance on a car that is unable to cope with all the possible driving scenarios. Robotic drivers are expected to be perfect. Major players such as Tesla and Waymo rely on highly detailed maps and very large sensor data in a race to build the ultimate robotic driver to cope with all possible driving scenarios. This approach optimizes for safety but delays the dream of fully autonomous cars. In this paper we consider robot-drivers as teen-drivers eager to learn how to drive but prone to mistakes in the beginning. The question we are trying to investigate is 'what if we allow autonomous cars to make mistakes like young human drives do?' In this paper, we explore reinforcement learning for small size autonomous vehicles fusing information from several sensors including a camera, color sensors, and sonar sensors. The robot-drivers have initially no information about the driving scenarios they learn with experience through a mechanism of rewards designed to quickly help our robot-teen to learn its driving skills.

Original languageEnglish
Title of host publicationProceedings - 2019 15th International Conference on Mobile Ad-Hoc and Sensor Networks, MSN 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages284-290
Number of pages7
ISBN (Electronic)9781728152127
DOIs
Publication statusPublished - 1 Dec 2019
Event15th International Conference on Mobile Ad-Hoc and Sensor Networks, MSN 2019 - Shenzhen, China
Duration: 11 Dec 201913 Dec 2019

Publication series

NameProceedings - 2019 15th International Conference on Mobile Ad-Hoc and Sensor Networks, MSN 2019

Conference

Conference15th International Conference on Mobile Ad-Hoc and Sensor Networks, MSN 2019
Country/TerritoryChina
CityShenzhen
Period11/12/1913/12/19

Keywords

  • Multi agents
  • Reinforcement Learning
  • Self-driving
  • Sensor Fusion

Fingerprint

Dive into the research topics of 'Robot drivers: Learning to drive by trial & error'. Together they form a unique fingerprint.

Cite this