Unveiling the Limitations of Onboard ADAS Sensors

Real-life Scenarios and Off-board VRU Detection Advantages

Get in touch
Unveiling the limitations of onboard adas sensors

Contactez-nous

Avant de remplir le formulaire d'inscription, veuillez lire le Privacy notice conformément à l'article 13 du règlement UE 2016/679
entrée non valable
entrée non valable
entrée non valable
entrée non valable
entrée non valable
entrée non valable

Privacy

Je déclare avoir lu et pleinement compris la note d'information sur la protection des données personnelles Privacy Notice et j'exprime par la présente mon consentement au traitement de mes données personnelles par Reply SpA à des fins de marketing, en particulier pour recevoir des communications promotionnelles et commerciales ou des informations concernant des événements ou des webinaires de l'entreprise, en utilisant des moyens de contact automatisés (par exemple, SMS, MMS, fax, e-mail et applications web) ou des méthodes traditionnelles (par exemple, appels téléphoniques et courrier papier).

In the last article, we have introduced the concept of “Smart Traffic Management”, an innovative approach that leverages both on-board and off-board ADAS sensors and computing to improve ADAS performances (see article here). Advanced Driver Assistance Systems (ADAS) have revolutionized road safety by leveraging onboard sensors to detect and mitigate potential risks. However, even with sophisticated sensor technologies, there are inherent limitations that can compromise their effectiveness, particularly in scenarios involving vulnerable road users (VRUs) like children. This article explores the challenges of onboard ADAS sensors and highlights the physical limitations and other opportunities with Off-Board ADAS.

Best example is easily visible through NCAP Hidden children Scenario.

Limitations of Onboard ADAS Sensors: NCAP Children Scenario example

One critical limitation of onboard ADAS sensors is their field of view (FOV). Due to physical constraints, sensors may have blind spots or areas with limited coverage, which can compromise their ability to detect objects accurately. In scenarios involving VRUs like children, who are smaller and can be hidden by other bigger objects, FOV limitations become more pronounced. For instance, consider the Hidden Children NCAP (New Car Assessment Program) scenario, where a child suddenly emerges from behind a parked vehicle into the path of an oncoming car. The FOV of the onboard sensors may fail to detect the child in time, leading to a potential collision.

Illustration from Euro NCAP website.

Actually, this scenario serves another purpose: it is mainly designed to challenge ego-vehicle’s braking performances by forcing a very late detection by On-board sensors leading to very late braking on short distance. OEMs are of course challenged to have accurate perception and react early enough, but this use case is also oriented on Braking performances.

However, using on-board/off-board perception solution, we can improve this kind of scenarios that are none-exclusive to NCAP protocol but also happening in real traffic environment.


Closing the Gap with Off-Board Solutions

To address the limitations of onboard ADAS sensors, off-board VRU detection information plays a crucial role. By utilizing a network of connected infrastructure and external systems, off-board solutions can provide real-time data about VRUs that might be outside the FOV of onboard sensors. This information can include the presence of pedestrians, cyclists, or children in the vicinity, allowing vehicles to proactively respond and mitigate potential risks.

City Traffic situation use case similar to NCAP Hidden children.

On Above situation, blue vehicle is most of the times not able to detect on-coming bycicle behind another obstacle. (In some case Radar and Lidar could have a detection, but usually Control Law needs more robust target from Sensor Fusion).

Off-board VRU detection solutions composed of several technologies, such as Vehicle-to-Everything (V2X) communication, Infrastructure cameras or radars, enable vehicles to receive vital information from surrounding infrastructure, other vehicles, and even pedestrians' personal devices. By leveraging this off-board data, onboard ADAS systems can enhance their capabilities and address the limitations of sensors alone. It allows vehicles to have a more comprehensive and accurate view of the surrounding environment, particularly in critical situations involving VRUs like children, where real-time information can be lifesaving.


Conclusion

While onboard ADAS sensors have significantly improved road safety, they face inherent limitations, particularly in scenarios involving VRUs like children. Off-board solutions, such as V2X communication, provide a valuable means to bridge the gap by offering real-time detection information that complements the capabilities of onboard sensors. By integrating both onboard and off-board technologies, we can strive towards a safer and more secure future for all road users.

Main challenges of such solution are mostly addressed by latency and ability to share the information and react on time. But this will be a dedicated topic in a next article.
  • strip-0

    Within the Reply Group, Autonomous Reply is the specialist in the specification, development, integration and validation of autonomous and connected embedded systems. We offer a portfolio of services covering the entire value chain, from strategy definition to implementation and operational safety. Autonomous Reply's services include consulting, real-time systems engineering, software development and integration of autonomous solutions.