Lecture on Bayesian Perception & Decision-making for Autonomous Vehicles and Mobile Robots (original) (raw)
Related papers
Tutorial on Autonomous Vehicles Technologies for Perception & Decision-Making
2018
Tutorial on "Autonomous Vehicles Technologies for Perception & Decision-making". New technologies for Autonomous Vehicles 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 tutorial 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...
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.
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.
2018
Thanks to the recent strong involvement of the Web Giants (GAFA) and of numerous international industrial companies and startups in the fields of car production, mobile robotics and mobility services, the concepts of Autonomous Vehicles and of Future Mobility Services is progressively becoming a reality connected to a huge expected market. More and more pre-products and innovative mobility services are both proposed and intensively tested in real world conditions. This is for instance the case with the commercially available Autopilot system of Tesla, or with the concept of Robot Taxi currently under testing in some US and Asian cities by companies such as Uber, Waymo or nuTonomy. Several millions of miles have been cover in the last decade by autonomous or semi-autonomous vehicles operating in real traffic environments, but at the expense of some benign or serious accidents due to insufficient safety conditions. The objective of this talk is to give a brief analysis of the state of...
Using Bayesian programming for multi-sensor multi-target tracking in automotive applications
… and Automation, 2003. …, 2003
A prerequisite to the design of future Advanced Driver Assistance Systems for cars is a sensing system providing all the information required for high-level driving assistance tasks. Carsense is a European project whose purpose is to develop such a new sensing system. It will combine different sensors (laser, radar and video) and will rely on the fusion of the information coming from these sensors in order to achieve better accuracy, robustness and an increase of the information content. This paper demonstrates the interest of using probabilistic reasoning techniques to address this challenging multi-sensor data fusion problem. The approach used is called Bayesian Programming. It is a general approach based on an implementation of the Bayesian theory. It was introduced first to design robot control programs but its scope of application is much broader and it can be used whenever one has to deal with problems involving uncertain or incomplete knowledge.