MSGID: 1:317/3 64927cf5   
   PID: hpt/lnx 1.9.0-cur 2019-01-08   
   TID: hpt/lnx 1.9.0-cur 2019-01-08   
    Self-driving revolution hampered by a lack of accurate simulations of   
   human behavior    
      
     Date:   
         June 20, 2023   
     Source:   
         University of Leeds   
     Summary:   
         Algorithms that accurately reflect the behavior of road users --   
         vital for the safe roll out of driverless vehicles -- are still   
         not available, warn scientists. They say there is 'formidable   
         complexity' in developing software that can predict the way people   
         behave and interact on the roads, be they pedestrians, motorists   
         or bike riders. To improve the modelling, a research team has   
         developed a simulation of how people behave on the roads based on   
         key cognitive theories.   
      
      
         Facebook Twitter Pinterest LinkedIN Email   
      
   ==========================================================================   
   FULL STORY   
   ==========================================================================   
   Self-driving revolution hampered by a lack of accurate simulations of   
   human behaviour.   
      
   Algorithms that accurately reflect the behaviour of road users -- vital   
   for the safe roll out of driverless vehicles -- are still not available,   
   warn scientists.   
      
   They say there is "formidable complexity" in developing software that   
   can predict the way people behave and interact on the roads, be they   
   pedestrians, motorists or bike riders.   
      
   To improve the modelling, a research team led by Professor Gustav Markkula   
   from the Institute of Transport Studies at the University of Leeds has   
   developed the first-ever simulation of how people behave on the roads   
   based on key cognitive theories.   
      
   Those separate theories were integrated into a larger, single   
   psychological model that would "describe behaviour in more complex,   
   real-world tasks."  During computer tests, the model accurately reproduced   
   various well-known but not previously understood behaviours of pedestrians   
   and drivers in common road scenarios. The model also predicted how   
   real-life human subjects would behave when facing interactive situations   
   in a virtual reality simulator.   
      
   Professor Markkula said: "These findings suggest that everyday road user   
   behaviour relies on a number of complex underlying cognitive mechanisms,   
   which may be part of the reason why it has been more difficult than   
   expected to create self-driving vehicles."  "Our research shows that   
   it is possible to integrate separate theories from psychology into   
   combined theories for applications such as simulating the way people   
   behave in traffic, which is something which has been called for but   
   rarely achieved."  The researchers' findings -- Explaining human   
   interactions on the road by large-scale integration of computational   
   psychological theory -- are published today (Tuesday, June 20) in the   
   scientific journal PNAS Nexus.   
      
   Algorithms needed to unlock self-driving revolution The development of   
   automated vehicles could have a major impact on the UK economy.   
      
   In a vision statement, the UK Government has said driverless vehicles   
   will launch a -L-42 billion industry and create 38,000 new jobs. The aim   
   is to see the start of the safe roll out of driverless vehicles by 2025.   
      
   But writing in the scientific journal PNAS Nexus, the researchers argue   
   that work towards driverless vehicles has been "hampered by a lack of   
   models of how human road users interact."  Accurate models are needed to   
   run simulations necessary in both development and testing of driverless   
   vehicles and their control systems, for example to demonstrate that the   
   vehicles remain safe when confronted with a range of human behaviour on   
   the road.   
      
   Up to now, most computer models of road user behaviour have been   
   statistically based, with predictions of how people might behave based   
   on analysis of large datasets, but typically without analysing those   
   models at a detailed behavioural level.   
      
   The research by Professor Markkula and his team has instead focused   
   specifically on the details of human behaviour and key concepts in   
   human psychology.   
      
   Road user behaviours and theories The researchers looked at several   
   typical human behaviours that exist on the road, such as hesitation   
   in unclear situations, or implicit communication using vehicle or body   
   movement to assert priority or to encourage someone else to go first.   
      
   The model predicts how people will behave by reference to key cognitive   
   theories. For example, one is "theory of mind," where people will form   
   beliefs about what someone else is doing and how their own behaviour   
   may affect decisions being made by the other. This relates also to   
   "behavioural game theory," explaining how people consider the combined   
   effects of their own behaviour and the behaviour of others when deciding   
   what to do.   
      
   Another theory incorporated in the model describes imperfect human   
   perception, requiring people to take time to assess and understand what   
   is going on in their environment.   
      
   Testing with human participants in the laboratory -- including the HIKER   
   pedestrian simulator at the University of Leeds Virtuocity facilities   
   - - revealed that the new psychological-theory based model could also   
   make correct predictions about driver-pedestrian interaction scenarios   
   studied in the experiments.   
      
   Professor Markkula, who holds the chair in Applied Behaviour Modelling   
   at Leeds, added: "Our research has shown that, by taking a number of   
   existing but separate mathematical theories about human psychology and   
   behaviour, and putting these together, we can model -- in much more   
   detail than previously possible -- how humans interact in road traffic,   
   for example as drivers or pedestrians, including phenomena such as   
   hesitation and interpretation of others' intentions."  In the paper,   
   the researchers say that much work remains to be done in the development   
   of psychological based models of road user behaviour.   
      
   The overall aim, say the researchers, is to develop computer models that   
   better reflect the human dimension to behaviour on the roads.   
      
   The authors of the paper -- Explaining human interactions on the road   
   by large- scale integration of computational psychological theory --   
   are Gustav Markkula, Yi-Shin Lin, Aravinda Srinivasan, Jac Billington,   
   Matteo Leonetti, Amir Hossein Kalantari, Yue Yang, Yee Mun Lee, Ruth   
   Madigan, and Natasha Mera. Matteo Leonetti is from Kings College London --   
   the others are based at the University of Leeds.   
      
       * RELATED_TOPICS   
             o Health_&_Medicine   
                   # Human_Biology # Mental_Health_Research #   
                   Workplace_Health # Medical_Topics   
             o Mind_&_Brain   
                   # Psychology # Social_Psychology #   
                   Brain-Computer_Interfaces # Behavior   
       * RELATED_TERMS   
             o Illusion_of_control o Theory_of_cognitive_development   
             o Aggression o Atmospheric_dispersion_modeling o   
             Cognitive_psychology o Cycling o Homosexuality o   
             Psycholinguistics   
      
   ==========================================================================   
   Story Source: Materials provided by University_of_Leeds. Note: Content   
   may be edited for style and length.   
      
      
   ==========================================================================   
   Journal Reference:   
      1. Gustav Markkula, Yi-Shin Lin, Aravinda Ramakrishnan Srinivasan, Jac   
         Billington, Matteo Leonetti, Amir Hossein Kalantari, Yue Yang,   
         Yee Mun Lee, Ruth Madigan, Natasha Merat. Explaining human   
         interactions on the road by large-scale integration of computational   
         psychological theory.   
      
         PNAS Nexus, 2023; 2 (6) DOI: 10.1093/pnasnexus/pgad163   
   ==========================================================================   
      
   Link to news story:   
   https://www.sciencedaily.com/releases/2023/06/230620113736.htm   
      
   --- up 1 year, 16 weeks, 1 day, 10 hours, 50 minutes   
    * Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1:317/3)   
   SEEN-BY: 15/0 106/201 114/705 123/120 153/7715 218/700 226/30 227/114   
   SEEN-BY: 229/110 112 113 307 317 400 426 428 470 664 700 291/111 292/854   
   SEEN-BY: 298/25 305/3 317/3 320/219 396/45 5075/35   
   PATH: 317/3 229/426