Robust object detection and tracking under arbitrary sight of view is challenging yet essential for the development of Autonomous Vehicle technology. With the growing demand of unmanned function vehicles, near-field scene understanding becomes an important research topic in the areas of low-speed autonomous driving. Due to the complexity of driving conditions and diversity of near obstacles such as blind spots and high occlusion, the perception capability of near-field environment is still inferior than its farther counterpart. To further enhance the intelligent ability of unmanned vehicles, in this paper, we construct a multimodal data collection platform based on 3 main types of sensors (Camera, LiDAR and Fisheye), which supports flexible sensor configurations to enable dynamic sight of view for ego vehicle, either global view or local view. Meanwhile, a large-scale multi-sensor dataset is built, named RoboSense, to facilitate near-field scene understanding. RoboSense contains more than 133K synchronized data with 1.4M 3D bounding box and IDs annotated in the full $360^{\circ}$ view, forming 216K trajectories across 7.6K temporal sequences. It has $270\times$ and $18\times$ as many annotations of near-field obstacles within 5$m$ as the previous single-vehicle datasets such as KITTI and nuScenes. Moreover, we define a novel matching criterion for near-field 3D perception and prediction metrics. Based on RoboSense, we formulate 6 popular tasks to facilitate the future development of related research, where the detailed data analysis as well as benchmarks are also provided accordingly.

Beijing (Gasgoo)- The Nasdaq-listed autonomous driving company TuSimple has entered into strategic cooperation with China's LiDAR supplier, RoboSense, TuSimple announced on April 14th. Per the cooperation, the two companies will focus on deploying RoboSense's RS-LiDAR-M1 intelligent solid-state LiDAR onto TuSimple's L2 and L4 autonomous commercial vehicles. The partners will work on mass-producing ADAS and autonomous driving system, and explore the potential of a high-performance, auto-grade, and production-ready integrated LiDAR perception solution under logistics scenarios. All in all, TuSimple believes that the cooperation will help accelerate the large-scale commercialization expansion of its autonomous commercial vehicles and AFN technology. In December last year, TuSimple had successfully completed the world's first fully autonomous test on open roads with its driverless heavy-duty trucks, without safety drivers or any other human interventions.

On September 18, 2019, RoboSense announced at Brussels, Belgium that its flagship product RS-LiDAR-M1 Smart LiDAR Sensor has been awarded the elite AutoSens Awards trophy in the "Best Automotive Safety System" category, given to only the highest-rated innovative product or technology in the automotive industry. This press release features multimedia. True autonomous driving requires human-like advanced sensing of the environment for driving with little or no human input. The safety of passengers and passers-by is always the priority concern for autonomous driving. When the RS-LiDAR-M1 is integrated into the current autonomous driving car perception system, it overcomes the weaknesses of millimeter wave radar and camera technologies on identifying obstacles, and eliminates car accidents, such as Tesla's recent cases, greatly improving the security of autonomous driving and ensuring passenger safety.

SHENZHEN, China & LONDON--(BUSINESS WIRE)--RoboSense, the leading supplier of LiDAR perception system solutions, and Aidrivers, the UK's leading provider of autonomous mobility solutions for industrial applications announced today a partnership in system integration. Aidrivers will integrate RoboSense Smart LiDAR Sensor System into their own Autonomous Driving Systems. Aidrivers is delivering a fully autonomous natural navigation system that meets industrial safety standards to seaports, particularly for horizontal transportation, aimed for improving operation efficiency and leading the way in industrial autonomous mobility automation. Their solution can work under all harsh weather conditions by achieving true 3D mapping and localization for precision positioning and situation cognisance and they are using RoboSense 3D LiDAR sensor technology, which collects stable and reliable environment information at near and far distance and under different weather conditions. "The performance of RoboSense 3D LiDAR products in harsh weather condition is impressive. We have been testing trailer vehicles under heavy rain and harsh weather conditions and our precision positioning system based on true 3D mapping and localization systems provides accurate localization result. The point cloud data quality in rainy days is excellent and outperforming state of the art."