ROBOSENSE
RoboSense LiDAR (https://robosense.ai/ ) today released the latest version of the ground truth data system and evaluation tool chain RS-Reference 2.1, used for LiDARs and multi-sensor fusion systems performance evaluation. The original RS-Reference version was launched in the market in 2016, when the automotive-grade MEMS solid-state LiDAR RS-LiDAR-M1 project was established. Used by global OEMs and Tier1s, the system has been continuously improved and upgraded with more efficient and useful evaluation function modules and software tool chains.
This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20210209005689/en/
While the evaluation function modules can be liked to an exam, the ground truth data is the "answer" for the evaluation of the perception system. Therefore, the accuracy of ground truth data must be significantly higher than the device under test (DuT) in all aspects including detection performance and geometric error.
The ground truth data, usually stored in the PB-Level, includes dynamic information such as obstacle types, speeds, and locations, and static information such as lane lines and road boundaries.
Data labeling quality and data generation efficiency are the key factors to ground truth data.
- The RS-Reference system provides a set of ground truth data generation and evaluation solutions, and outputs detection performance and geometric error indicators with a labeling efficiency close to 1:1. This is significantly more accurate than real-time perception, manual labeling and traditional labeling tools.
- High performance and mature sensor data collection system: the RS-Reference system contains the RoboSense 128-beam LiDAR RS-Ruby, Leopard camera, Continental 408 millimeter-wave radar, GI-6695 RTK, and two added RoboSense RS-Bpearl LiDAR for near-field blind spots in the 2.1 version.
- Detached roof-mounted deployment without vehicle body modification: the RS-Reference system adapts to different vehicle sizes, does not occupy the sensor installation position of the DuTs, and directly evaluates the intelligent driving system that is consistent with the sensor sets of commercial vehicles.
- Vastly improved/accumulated perception algorithm and offline processing mechanism: The algorithm is key to smart labeling instead of manual labeling, and is responsible for the extraction of ground truth data. The RS-Reference system uses a customized and dedicated offline perception algorithm, which is the product of RoboSense’s 13+ years’ of accumulated experience of LiDAR sensing algorithm technology. It performs a “full life process tracking and identification" for each obstacle data, and extracts all ground truth data from each frame. The RS-Reference system can pick up speed and acceleration labeling, and accurately delineate the size of the labeling frame through comprehensive shape and size information. The system is also capable of accurately dividing obstacles that are in close proximity to each other in complex scenes.
- Full-stack evaluation tool chain: it includes data collection tools, sensor calibration tools, visualization tools, manual verification tools, evaluation tools, etc. The 2.1 version upgrades the data management platform and adds the scene semantic labeling function that serves every step of the evaluation process.
- Individual sensor evaluation in the multi-sensor fusion system: not only can the RS-Reference system evaluate the result of intelligent driving's perception fusion, but it can also provide targeted solutions based on the features of different types of sensors such as LiDAR, millimeter wave radar, and camera. Dedicated or customized tool modules can be developed according to customer needs for further in-depth analysis of the performance of the sensing system.
- Extended application value of the RS-Reference: includes planning and control algorithm development support, which is able to generate massive ground truth data to build simulation scenes, and can evaluate road-side perception systems.
View source version on businesswire.com: https://www.businesswire.com/news/home/20210209005689/en/
Link:
Social Media:
About Business Wire
Subscribe to releases from Business Wire
Subscribe to all the latest releases from Business Wire by registering your e-mail address below. You can unsubscribe at any time.
Latest releases from Business Wire
Suzano Forms Partnership with Tencent and Ecofuturo Institute at COP30 for AI-Powered Conservation and Nature Education20.11.2025 18:25:00 CET | Press release
New agreement signed at COP30 will see organisations collaborating to use artificial intelligence tools for biodiversity monitoring and digital platforms to boost public engagement in conservation efforts. The world’s largest pulp supplier, Suzano, today announces the signing of a Memorandum of Understanding (MoU) with the multinational technology business Tencent and the Brazilian non-profit Ecofuturo Institute, to pioneer new digital approaches to drive public engagement in conservation. The collaboration will leverage Suzano’s expertise in sustainable forestry, Tencent’s cutting-edge digital technology, and Ecofuturo’s expertise in environmental education, to pilot joint initiatives in both Brazil and China. These include enhancing ecological awareness, accelerating biodiversity solutions, and leveraging digital platforms to foster public engagement in conservation. The partnership will result in a pilot project where advanced AI tools for species recognition developed by Tencent’s
EMVCo Working on How Global Specifications Can Support Agentic Payments20.11.2025 17:38:00 CET | Press release
EMVCo – the technical body that creates and manages EMV® Specifications and programmes that enable seamless and secure card-based payments worldwide – has announced that it is working on how global specifications can support innovation in agentic payment solutions by increasing trust and interoperability across the ecosystem. Agentic commerce is rapidly reshaping the shopping experience by enabling AI agents to act on the consumer’s behalf. This is driving significant momentum for agentic payments, which introduce AI agents as new actors that can initiate transactions with merchants – without requiring direct involvement from the consumer. While agentic payments have the potential to increase convenience and personalisation, they present unique considerations for how transactions are initiated, authenticated and secured. As industry adoption and innovation accelerate, a globally interoperable and scalable approach may be beneficial in realising trusted agentic payments for consumers, m
Université Paris-Saclay and Owkin: A Unique Alliance to Propel University Medical Research to the Top of the European Rankings Through AI20.11.2025 15:17:00 CET | Press release
Université Paris-Saclay and Owkin announce the signing of a memorandum of understanding to explore the potential of K Pro Free - Owkin’s AI co-pilot for biology - for use by Paris-Saclay. This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20251120130113/en/ K Pro Free will now be available to the entire Université Paris-Saclay community, and in particular teachers, researchers and doctoral students working in the biomedical sciences. The partnership includes workshops, training sessions and events designed to promote the discovery and adoption of K Pro Free, as well as the co-organization of communication and dissemination initiatives around the use of AI in health. In this way, the partnership will promote user training, but also enrich and continuously improve the co-pilot's models through feedback and use cases from the l’Université Paris-Saclay community. This partnership is part of Université Paris-Saclay’s strategy to integr
Frasca Advances Flight Training Technology with New Visual System Powered by Unreal Engine20.11.2025 15:05:00 CET | Press release
Frasca International, Inc., a FlightSafety International company and leader in flight simulation, today announced the launch of VITAL FVS 100, the next evolution of its visual system technology. Building on the proven TruVision Global platform, VITAL FVS 100 was developed using Epic Games’ Unreal Engine and delivers unprecedented realism, scalability, and innovation in pilot training. The Unreal-powered VITAL FVS 100 system introduces major advancements in visual fidelity and training realism, further enhancing the capabilities of Frasca, a leading developer of flight simulators and training devices. The new system includes physically based renderings, advanced lighting effects, and a new volumetric cloud model that creates dynamic, weather-rich environments. Terrain imagery now includes one-meter resolution coverage for the contiguous United States and Hawaii, with expanded global datasets covering European buildings and tree covered regions. Additionally, enhanced particle effects re
GigaOm Radar for Vector Databases v3 Positions Vespa.ai as a Leader and Outperformer20.11.2025 15:00:00 CET | Press release
Vespa Recognized for Integrated Ranking, Multimodal Search, and Production-Scale AI Performance Vespa.ai, the creator of the AI Search Platform for building and deploying large-scale, real-time AI applications powered by big data, today announced its recognition as a Leader and Outperformer in the GigaOm Radar for Vector Databases v3, marking the company’s third consecutive year being evaluated in GigaOm’s vector database research. Now in its third edition, the report compares 17 leading open source and commercial solutions using GigaOm’s structured evaluation framework. In addition to core table-stakes capabilities, the Radar reviews each vendor’s key features, emerging strengths, and broader business criteria. The shift from Sonar to Radar reflects the technology’s transition into mainstream adoption. GigaOm names Vespa.ai a leader for its ability to manage complex data, optimize results at scale, and support multimodal AI workloads. The report highlights Vespa’s native tensor suppor
In our pressroom you can read all our latest releases, find our press contacts, images, documents and other relevant information about us.
Visit our pressroom