BYD AI Team Unveils HyWorldVLA Hybrid Model Achieving 90.59 PDMS on NAVSIM Benchmark
- Published
- Source
- PanDaily.com
The BYD AI team has introduced the HyWorldVLA, a hybrid pixel-latent world model that utilizes VLA architecture. This model has achieved a score of 90.59 PDMS on the NAVSIM benchmark, marking a significant milestone for BYD in the field of autonomous driving foundation models.
This achievement is noteworthy as it highlights BYD's commitment to advancing autonomous driving technologies. The collaboration with researchers from HIT robotics underscores the importance of interdisciplinary efforts in developing state-of-the-art models that can enhance vehicle autonomy and safety.
Looking ahead, the performance of the HyWorldVLA on the NAVSIM benchmark sets a high standard for future developments in autonomous driving models. No further timeline was disclosed at the time of publication.
Original report
BYD AI Team Revealed for First Time: HyWorldVLA Hybrid World Model Achieves SOTA on NAVSIM v1 With 90.59 PDMS Marking BYD Entry Into Autonomous Driving Foundation Models
PanDaily.com · [email protected] (Pandaily)This 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
RobotToday Weekly October 26 – 30, 2026 RobotToday · 1 day ago
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
Related Suppliers
Insight Intelligence 具识智能
Shanghai developer of insightOS, an embodied-AI robot operating system spanning dev, runtime and fleet ops; HIT spin-out with deployments at BYD.
Lightwheel
Physical AI infrastructure company providing SimReady assets, egocentric data, and evaluation platforms to train and deploy robots at scale.
Vassar Robotics
San Francisco robotics startup founded 2025 by Charles Yong; YC X25-backed maker of the Navrim robot arm kit and direct-drive actuator hardware.
Helm.ai
US autonomous driving AI software company providing perception, planning, and simulation models for ADAS to Level 4 vehicles, backed by Honda and Volkswagen.
Yaak Technologies GmbH
Berlin AI startup founded 2020, collecting multimodal driving data across 30+ German cities to train foundation models for autonomous vehicles and robotics.
MVP Robotics
Bradford, Vermont firm founded 2013 making M2P autonomous UGVs, HEKTR robotic targets and tackling dummies; first DoD contracts in 2018.
WowWee Group Limited
Hong Kong toy-robotics company founded 1988 by the Yanofsky brothers; creator of Robosapien and Fingerlings, employing around 100 people.
ESPROS Photonics Corporation
Swiss fabless semiconductor company designing ToF imaging chips and 3D camera modules for robotics, industrial automation, and automotive sensing.
Hangzhou TorchKernel Robotics Co., Ltd. 杭州炬坤机器人有限公司
Hangzhou start-up building industrial dexterous hands; its 21-DOF TORCH HAND 1 weighs 1.1 kg and carries 40 kg peak, alongside the 480 g TORCH HAND 2.
Anyverse Dynamics 无界动力
Beijing embodied-AI startup founded in 2025 by ex-Horizon Robotics leaders; builds the K15 wheeled dual-arm robot and the MWA embodied robot brain.
Physical Intelligence
San Francisco AI robotics company founded 2024; its pi0 vision-language-action models direct many robot types, backed by billions in venture funding.
AutoX Inc. 安途科技
California-founded autonomous vehicle company operating Level 4 driverless RoboTaxi services in China, with the largest fully driverless fleet in the country.
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.