Project

Advanced  Driver  Assistance  Systems  (ADAS)  and  autonomous  driving  (AD)  are  progressing  towards higher speeds and more complex dynamic scenarios, where the on-board sensor systems may not be sufficient to provide adequate awareness of traffic situation for accurate and timely situation assessment and action. That is why the connected vehicles technologies, such as vehicle-to-everything  (V2X)  communication,  are  receiving  attention  as  enabling  sharing  the  accurate  position  information  between  vehicles. As  the  share  of  V2X  equipped  vehicles  is  currently  too  small, stationary V2X equipped traffic sensors are a promising solution, as these can detect and share the information about all objects present in a specific road section. Particularly, cooperative perception, also known as collective perception, realized by fusing the object data sensed by the on-board  sensors  with  information  received  from  the  infrastructure  sensors,  has  potential  to  bring  together  driving  automation  technology  with  V2X  communication.  However,  cooperative  perception  is  heavily  dependent  on  the  timeliness  of  the  data  received  by  a  connected  vehicle.  Thus, one of the great challenges is to study how the latency affects the performance of the AD or ADAS functionalities in dealing with safety critical traffic cases. Such a study would enable to set the  requirement  on  latency  of  V2X  communication  systems  based  on  safety  requirement  of  AD/ADAS functions.

Purpose and Goals

The research question we want to address in this pre-study is: determine the latency requirements for  collective  perception  systems  to  enable  AD/ADAS  function  to  fulfil  the  state-of-the-art  safety  norms  in  a  realistic  traffic  use  case.  To  approach  this  question,  we  aim  to  achieve  the  following  objectives: (i)establish a tool chain data-scenarios-simulation-requirements, (ii) understand the needed pieces/shortcomings of the data and tools, and (iii) apply for a larger project to continue building the framework.

Design and Implementation

To approach the research question and the derived objectives  the following work packages are proposed: (1)  collecting  the  data  on  the  interactions  between  cars  and  unprotected  road  users  using  already  installed  Viscando  stationary  3D  and  AI-based  sensors; (2)  identifying  different  scenarios  from  the  data  collected  with  the  Viscando  sensors;(3)  simulating  the  identified scenarios  using  the  MATLAB  Automated  Driving  Toolbox;  and  (4)  investigating  the  maximum  acceptable end-to-end delay that meet the safety requirements in such scenarios.

Expected Results

With this pre-study we start working with the traffic measurement data and expect to get a better understanding possible  benefits  of,  and  requirements  for  collective  perception  for  improved  ADAS and AD functions in real-world scenarios. Moreover, the present pre-study should generate a  larger  successful  project  application.  We  are  potentially  aiming  at  VINNOVA  FFI  project  with  Zenseact AB and Viscando AB. Thus, we see the current application as a bridge towards this larger initiative,  which  in  turn,  will  allow  us  to  present  the  results  in  prestigious journals  or  scientific  conferences.