Researchers Develop Language Model System for Personalized Self-Driving Car Requests
- Published
- Source
- IEEESpectrumAI
Researchers at Delft University of Technology (TU Delft) have created a system that allows passengers to influence the driving style of autonomous vehicles using natural language requests. This system utilizes a large language model (LLM) to interpret user instructions, such as adjusting speed or smoothness based on individual preferences, while maintaining safety through a motion-planning algorithm.
The significance of this development lies in its potential to enhance user experience in self-driving cars by making them more adaptable to personal preferences. By allowing passengers to communicate their needs in everyday language, the system aims to bridge the gap between human driving styles and autonomous vehicle behavior, ensuring a smoother and more comfortable ride.
Looking ahead, the researchers plan to further refine the system and explore its applications in real-world scenarios. The system's interactive nature, which allows for continuous adjustments based on passenger feedback, could pave the way for more personalized and user-friendly autonomous driving experiences. No further timeline was disclosed at the time of publication.
Original report
Self-Driving Cars Could Someday Take Requests
IEEESpectrumAI · Edd GentThis briefing is an independently written summary based on publicly available reporting and is provided for industry information and news discovery. The original report and source publication are credited and linked where applicable. RobotToday does not claim ownership of third-party source material.
Rights concerns? Contact [email protected] with the relevant URL and details. We will review the matter and take appropriate action where warranted.
More related news
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
Related Suppliers
Duckietown Robotics
United States
Educational robotics platform provider offering autonomous vehicle kits and AI curricula used by 250+ universities worldwide.
Ottopia
Israel
Ottopia is an Israeli AI & machine learning platform company that provides a Hybrid AI teleoperation platform enabling humans and AI to co-pilot autonomous.
Jacobi Robotics
United States
AI-powered robot motion planning software enabling collision-free trajectory planning and mixed-case palletizing for industrial robot arms.
UltiMaker
Netherlands
Utrecht, Netherlands FDM 3D-printer maker founded 2011; merged with MakerBot in 2022 to form UltiMaker, owned by NPM Capital and Stratasys.
OpenAI
United States
US AI research lab and product company founded 2015; develops GPT, DALL-E, and robotics/embodied AI foundation models targeting physical-world AGI.
Weilan Tech 南京威兰德智能科技有限公司
China
Chinese robotics company (Nanjing, est. 2019) making the BabyAlpha quadruped companion robot — world's top-selling consumer robot dog, 25,000+ units sold.
Guangzhou PHYBOT Technology Co., Ltd. 广州动易人工智能科技有限公司
China
Guangzhou embodied-intelligence startup building bipedal humanoid and four-wheel-legged robots under the PHYBOT brand.
Unlimited Tomorrow
United States
US company developing TrueLimb, an affordable custom 3D-printed multi-articulating bionic prosthetic arm for people with upper limb differences.
Rivian
United States
American EV maker building R1T pickup, R1S SUV and commercial vans, with an in-house Level 2+ Rivian Autonomy Platform.
4rge.ai
United States
US startup developing intelligence-defined IMUs and GNSS/INS navigation systems for industrial and consumer automation applications.
University of Szeged, Faculty of Science and Informatics
Hungary
Hungarian university with Hungary's oldest AI research group (RGAI, est. 1969) and robotics-related informatics and machine learning programs.
Stanford Artificial Intelligence Laboratory
United States
Stanford, California university AI research lab founded 1963 by John McCarthy; about 25 faculty work on machine learning, robotics, vision, and NLP.
Robotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
Join the RobotToday community on LinkedIn
Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.
