Tutorial on Autonomous Vehicles Technologies for Perception & Decision-Making (original) (raw)

Lecture on Bayesian Perception & Decision-making for Autonomous Vehicles and Mobile Robots

2017

New technologies for Autonomous Vehicles and Mobile Robots will be presented, with an emphasis on multi-sensors Embedded Perception, Situation Awareness, Collision Risk Assessment, and Decision-making for safe navigation in Dynamic Human Environments. It will be shown that Bayesian approaches are mandatory for developing these technologies and for obtaining the required robustness in presence of uncertainty and complex dynamic situations. The talk will be illustrated by some interesting results obtained in the scope of several collaborative projects involving either national research and development institutes such as CEA-LETI and IRT (Technological Research Institute) Nanoelec, or international industrial companies such as Toyota or Renault-Nissan.

Embedded Bayesian Perception and Collision Risk Assessment (invited talk)

2017

The lack of robustness and of efficiency of current Embedded Perception and Decision-making systems is one of the major obstacles to a full deployment of self-driving cars. In this talk, it will be argued that three enabling technologies are required for improving the capabilities of such systems: (1) a framework for fusing multiple-sensor data in the presence of uncertainty and for interpreting in real-time the surrounding dynamic environment, (2) a method for predicting future environmental changes using perception history, contextual information and some prior knowledge, and (3) a decision-making approach having the capability to continuously evaluate the risk of future collisions and to provide on-line maneuvers recommendations for a safe navigation. New approaches developed at Inria for Embedded Multi-sensors Perception, Situation Awareness, Collision risk assessment and on-line Decision-making for safe navigation, will be presented. It will be shown that Bayesian approaches ar...

Towards Fully Autonomous Driving ? The Perception & Decision-making bottleneck

2016

Thanks to the DARPA Urban Challenge in 2007, the launch a few years later of the Google Car project, the recent multiple announcements of the Automotive Industry, and the wide dissemination by the media of nice interviews and videos, the concept of Autonomous Driving seems to progressively become a reality for the next decades. The objective of this talk is to give a brief analysis of the state of the art, before focusing on one of the current brake on the deployment of such a technology: the lack of robustness and of efficiency of current Embedded Perception and Decision-making systems. New technologies and trends will be presented for addressing these issues. It will be shown that Bayesian approaches are mandatory for developing such technologies and for obtaining the required robustness in presence of uncertainty and complex dynamic situations. The talk will be illustrated by some interesting results obtained at Inria in the scope of several collaborative projects involving Toyot...

Embedded Sensor Fusion and Perception for Autonomous Vehicle

2019

Invited Talk.This talk presents a novel Embedded Perception System based on a robust and efficient Bayesian Sensor Fusion approach. The system provides in real time (1) the state of the dynamic environments of the vehicle (free space, static obstacles, dynamic obstacles along with their respective motion fields, and unknown areas), (2) the predicted upcoming changes of the dynamic environment and (3) the estimated short-term collision risks (about 3s ahead). This approach has been developed and patented by Inria and IRT (French Technological Research Institute) Nanoelec. In 2018, an exploitation license was sold to Toyota Motor Europe and to an industrial company working in the field of Autonomous Shuttles (confidential). The approach is illustrated by some recent results obtained in cooperation with Toyota, Renault and the French IRT Nanoelec.

Situation Awareness & Decision-making for Autonomous Driving

2019

Invited Talk. Motion Autonomy and Safety issues in Autonomous Vehicles are strongly dependent upon the capabilities and performances of both Embedded Perception and Decision-making systems. This talk presents how it is possible to address these important issues by mixing Bayesian and Machine Learning approaches. The talk will be illustrated using results obtained by Inria Grenoble Rhone-Alpes (France) in the scope of several R&D projects conducted in collaboration with IRT Nanoelec (French Technological Research Institute) and with several industrial companies such as Toyota or Renault.

Embedded Bayesian Perception and Risk Assessment for ADAS and Autonomous Cars (Keynote Talk)

2015

This talk addresses both the socio-economic and technical issues which are behind the development of the next generation of cars. These future cars will both include enhanced Advanced Driving Assistance Systems and Driverless Car functionalities. In the talk, new Bayesian approaches for Autonomous Vehicles will be presented, with an emphasis on Situation Awareness, Collision Risk Assessment, and Decision-making for safe navigation and maneuvering. It will be shown that Bayesian approaches are mandatory for developing such technologies and for obtaining the required robustness in presence of uncertainty and complex traffic situations. Results obtained in cooperation with Toyota and with Renault will also been presented.

Autonomous vehicle perception: The technology of today and tomorrow

Transportation Research Part C: Emerging Technologies, 2018

Perception system design is a vital step in the development of an autonomous vehicle (AV). With the vast selection of available off-the-shelf schemes and seemingly endless options of sensor systems implemented in research and commercial vehicles, it can be difficult to identify the optimal system for one's AV application. This article presents a comprehensive review of the state-of-the-art AV perception technology available today. It provides up-to-date information about the advantages, disadvantages, limits, and ideal applications of specific AV sensors; the most prevalent sensors in current research and commercial AVs; autonomous features currently on the market; and localization and mapping methods currently implemented in AV research. This information is useful for newcomers to the AV field to gain a greater understanding of the current AV solution landscape and to guide experienced researchers towards research areas requiring further development. Furthermore, this paper highlights future research areas and draws conclusions about the most effective methods for AV perception and its effect on localization and mapping. Topics discussed in the Perception and Automotive Sensors section focus on the sensors themselves, whereas topics discussed in the Localization and Mapping section focus on how the vehicle perceives where it is on the road, providing context for the use of the automotive sensors. By improving on current state-of-the-art perception systems, AVs will become more robust, reliable, safe, and accessible, ultimately providing greater efficiency, mobility, and safety benefits to the public.