Cognition refers to intelligent behaviour, the essential characteristic of living beings. In humans, this behaviour is based on key cognitive capacities such as perception, action, emotion, language, learning, memory, reasoning and consciousness.

Cognitive robotics is about developing intelligence in robots. The Cognitive Robotics research group at TU Delft focuses primarily on how robots can best plan and carry out their subsequent actions, so three cognitive aspects come into play: perception, thinking and acting.

The Department of Cognitive Robotics brings together Delft robotics research, which used to be divided into two separate departments: Systems and Control and Biomechanical Engineering. Our research focuses on:

  • Learning and autonomous control
  • Robot dynamics
  • Human-robot interaction
  • Intelligent vehicles
     

The fundamental work of the Department of Cognitive Robotics is used in various Delft field labs, where practical robot applications are being developed and tested on a small scale (RoboHouse, SAM|XL and AIRLab Delft). From these field labs, the work eventually finds its way into practical applications in numerous industries, agriculture and horticulture, and retail.

Cooperation / partners

News

David Abbink in various media

AGConnect: Zorgrobots, laveren tussen utopie en dystopie (Dutch) NWO: Buiten de lijntjes (Dutch) De Ingenieur: Cobots: een robot als collega (Dutch) / September 2022 issue (Dutch) Nieuwsbreak: David Abbink wil robots gaan maken waar de mens wél blij van wordt (Dutch) NRC: Met zijn allen een góéde robot maken; TechniekRobots waar je blij van wordt (Dutch) FMT Gezondheidszorg: Zijn robots in de ouderenzorg realistisch? (Dutch) NRC: David Abbink wil robots gaan maken waar de mens wél blij van wordt (Dutch) ICT&Health: Inzet zorgrobots steeds realistischer (Dutch) Nationale Onderwijsgids: Inzet van zorgrobot wel steeds realistischer (Dutch) NOS: Robot voorkomt straks dat ouderen medicijnen vergeten, voorziet Helder (Dutch) Vrij Nederland: Robots zouden werk leuker moeten maken, niet makkelijker (Dutch) Medical Facts: Zorgrobots lijken niet op mensen (Dutch) NOS: Robots oplossing voor personeelstekorten in de zorg? 'Idee wordt overschat' (Dutch) Nieuwsuur: Zorgrobots de toekomst? (Dutch) Bits&Chips: TU Delft develops proactive eco mode with Renault (English) Klimaatweek: TU Delft ontwikkelt een auto die vooruit kan kijken met slimme eco-modus (Dutch) Eindhovens Dagblad: Zuinig rijdende auto’s worden sneller door Nederlandse vinding (Dutch) Autoweek: TU Delft werkt met Renault aan 'slimme eco-modus' (Dutch) De Ingenieur: Rijden in eco-modus: nu met snelle acceleratie (Dutch) Verkeerskunde: Delftse robotingenieurs ontwikkelen auto die ‘vooruit kan kijken’ (Dutch) Tweakers: TU Delft ontwikkelt eco-modus waarmee auto soms meer vermogen kan leveren (Dutch) MSN: TU Delft werkt met Renault aan 'slimme eco-modus' (Dutch) India Education Diary: TU Delft: TU Delft develops a car that can ‘look into the future’ with smart eco mode (English)

Drivers of automated vehicles are blamed for crashes that they cannot reasonably avoid

People seem to hold the human driver to be primarily responsible when their partially automated vehicle crashes. But is this reasonable? In a paper recently published in Nature Scientific Reports , researchers from the AiTech Institute investigated the mismatch between the public’s attribution of blame and finding from the human factors literature regarding human’s ability to remain vigilant in partially automated driving. Participants of the experiment blamed the driver primarily for crashes, even though they recognized the driver’s decreased ability to avoid them. The public expects drivers to remain vigilant and supervise the automated vehicle at all times, yet we know this is an unreasonable demand for a human driver; even highly-trained pilots struggle with supervising autopilot systems for prolonged periods. Drivers are unaware of what is happening in their surroundings, and they cannot respond as fast as the system requires. The imbalance between human-factor-related challenges with automation regarding driver ability and the participant’s responsibility attributions reveals a culpability gap. In this culpability gap, responsibility is not reasonably distributed over the involved human agents; the driver receives most blame, yet this may be unreasonable given their impacted ability to change the outcome. The findings of this work have implications. In terms of public discourse, based on the participants’ arguments, it seems that the majority of our participants do not consider the aforementioned human-centered challenges of automated driving in their responsibility attribution. This could indicate that humans are unaware of these effects of automation, which could lead to ‘unwitting omissions’. Drivers are unaware of the impact of automated driving on their ability to perform the required driving tasks should they need to, yet they are still considered to be responsible by their peers. The AiTech Institute focuses on the concept of meaningful human control over AI systems, in other words: humans and not computers and their algorithms remail morally responsible for relevant decisions. "The AiTech Institute leads interdisciplinary research around the concept of 'meaningful human control over AI systems'. This concept cannot be studied from one discipline, and so AiTech encourages researchers from different fields to learn each other's scientific language and then work together on complex issues, such as the topic of this study," says scientific director and professor David Abbink. The researchers argue that the responsibility attributed to a driver should be consistent with their ability to control the automated vehicle. If that ability is impacted by using the automation, responsibility should shift from the driver to the automation (or its manufacturer), which raises the question whether our participants’ ratings are reasonable. Providing public information about the driver-centered challenges associated with automated driving could be helpful, as well as driver training. MORE INFORMATION Click here to read the full paper, authored by Niek Beckers , Luciano Cavalcante Siebert , Merijn Bruijnes , Catholijn Jonker & David Abbink .
/* */