Lessons learned “In-vehicle technology enablers”
Lessons learned can significantly help future R&I initiatives by providing key information on the results achieved. The table below includes the lessons learned, collected so far, which are related to “In-vehicle technology enablers”:
|Type of lesson learned||Topic||Project name||Deliverable||Brief Summary of lesson learned|
|Technical||Technology readiness and availability||MuCCA||MuCCA Project Website||The project has struggled to find a suitable of-the-self solution for a perception system that met the project requirements in terms of performance (long-range motorway speed), cost and maturity. The sensor market has been evolving quickly but there´s no cost-effective solution yet compared to other sources of data to feed localisation (i.e.: enhanced GPS and comms).|
|Technical||Features and performance vs. computer power available||MuCCA||MuCCA Project Website||The hardware had an adequate performance for our final demonstration, but probably some struggles would have been found if the full perception system originally expected to implement, and human driver model, were running simultaneously. A performance upgrade is already in progress however.|
|Technical||Distributed/semi-decentralized Control of Automated Vehicles||AutoNet2030||D1.3 Public Final Report (Chapter 7.1)||An iterative development framework is needed for distributed control. Cooperative control is highly dependent on perception and communication components.|
|Technical||Perception Layer to Cope with Different Vehicle Platforms||AutoNet2030||D1.3 Public Final Report (Chapter 7.1)||Additional plausibility and consistency checks should be implemented in parallel to the perception in order to handle complexity and safe detection of potential failure states of the whole system.|
|Technical||Building High-accuracy Positioning Solutions||AutoNet2030||D1.3 Public Final Report (Chapter 7.1)||Τhe implemented positioning technology is considered to be very well matching the positioning accuracy requirements of automated driving. Future efforts may include addressing issues related to overhead obstacles or urban canyons.|
|Technical||Integrated Systems for Future Vehicle Automation||AutoNet2030||D1.3 Public Final Report (Chapter 7.1)||When working with standardized interfaces and isolated modules, one must focus on architectural questions and specifications of the interfaces very early in the project.|
|Technical||-Automation in close distances|
-Automation in urban scenarios
-Automation in highway scenarios
|AdaptIVe||D1.0 Final project results (chapter 12.1)||Lessons learned in bullet points in the deliverable.|
|Legal & regulations||Sharing video footage for research purposes should be made easier by providing EU-level practices and worked-examples||L3Pilot||Upcoming L3Pilot D5.2||The legal situation regarding sharing e.g. car front view video files between a research consortium’s partners seems to be a moving target with various views. Therefore, research projects would welcome EU-level practices and legal templates for sharing video from a vehicle within a research consortium, to speed up work and to avoid lengthy legal preparations and different interpretations. The current best practice might be to add video data sharing clauses to the consortium agreement, to reduce the need for bilateral agreements.|
Summarising the table above, one could state cost-effective of-the-shelf perception and localisation solutions don’t exist today. Also one should consider the computing power necessary to run smoothly perception system and driver models. An iterative process while developing in-vehicle components (incl. control) should be adopted including plausibility and consistency checks. When working with standardized interfaces and isolated modules, one must focus on architectural questions and specifications of the interfaces very early in the project. Apart from technical issues it is important for research and innovation purposes, as well as implementation ones, to find solutions to problems for sharing “sensitive” data e.g. the video footage of experimental vehicles.
Have feedback on this section? Let us know!
Please add your feedback in the field below.
Your feedback has been sent!
Thank you for your input.
An error occured...
Please try again later.