Autonomous and Self Driving Car News

Venti Tech Benchmarked

Venti Technologies, the leader in safe-speed autonomous vehicles for moving people and goods,  announced that its innovative, patented driverless software platform has benchmarked #1 in the world for its Perception System. Venti’s deep learning-based technology, borne out of leading-edge research from leading academic laboratories, uses unique algorithms to merge obstacle detection with vector velocity. In combination with Venti’s modular architecture that integrates localization and route planning, the Perception System enables autonomous vehicles to detect threats and avoid obstacles with real-time response and re-planning. Importantly, perception is recognized as the foundation of an autonomous vehicle system.

Venti Technologies’ Perception System performance was evaluated by KITTI, an autonomous vehicle performance benchmark used around the world. The evaluation benchmarked Venti’s novel algorithm which takes an image and its corresponding point cloud as inputs, and outputs all the obstacle locations and their velocity. The key idea behind Venti’s technology is to combine the obstacle detection and velocity estimation within the same deep learning network, establishing an end-to-end learning framework. The network learns obstacles’ deep features and their corresponding velocity features jointly. The use of 3D information further improves both obstacle detection and velocity estimation accuracy, producing a superior evaluation in the benchmark study.

“This achievement signifies tremendous success for our novel AI-based approach to autonomous mobility,” commented Shuyan Zhao PhD, co-Founder and Chief Operating Officer of Venti. “We are thrilled with these results, and look forward to continuing to work with our partners and customers to incorporate our technology into more forms of mobility and thus disrupt the global transportation market.”

Xinxin Du, PhD, Founder and Chief Technology Officer of Venti, stated, “Our next-generation automotive vehicles, AV 3.0, represent a unique breakthrough in mature driverless technology. We provide state-of-the-art obstacle perception, avoidance and maneuvering by using rigorous mathematical modeling and theoretically grounded algorithms that ensure adaptivity to changes in the environment. We are very proud of the real-world innovation that our leadership in computer science, artificial intelligence and electrical engineering has been able to deliver.

Spirent Releases SimHIL

Spirent Communications plc (LSE:SPT), the world leader in global navigation satellite systems (GNSS) testing solutions, has announced the release of SimHIL, an integrated hardware-in-the-loop (HIL) testing software API for Spirent GNSS simulators. SimHIL brings high fidelity GNSS signal simulation with low latency to automotive industry HIL testbeds.

Spirent’s SimHIL software has been developed to meet the automotive industry’s growing need for realistic positioning, navigation and timing testing for sensor fusion. As customers apply increasing pressure on car manufacturers for more advanced driver-assistance system (ADAS) features and advanced infotainment systems, test labs need to be able to combine Wi-Fi, camera, lidar, radar, inertial and GNSS data that power these advanced automotive systems.

SimHIL helps test engineers bring accurate, controlled and coherent data from GNSS and inertial sensors to their sensor fusion algorithms within HIL test environments. Facilitating the ultra-low latency, complete control, enhanced realism, and ease of use and setup of Spirent GSS7000 and GSS9000 GNSS simulators, SimHIL is an ideal solution for OEMs and tier-one suppliers developing ADAS, V2X and sensor fusion engines.

The new SimHIL API enables:

• External motion input –real-time direct motion and trajectory data input from simulators.
• Sensor fusion – introducing GNSS signals into sensor fusion engines.
• V2X testing – validation and performance benchmarking of V2X applications.
• Infotainment system testing – real-time scenario feedback to system and driver responses.
• Vehicle-in-the-loop (VIL) – final production form product testing.
• Accurate testing – reliable results supported by ultra-low latency simulation. Criticality of ADAS features, such as lane assist and automatic braking, mean that 3+ metres of uncertainty introduced by higher latency systems is not sufficient.

Martin Foulger, General Manager of Spirent’s Positioning, Navigation and Timing Business said: “With our SimHIL software and GNSS simulators, test engineers can bring realistic, controlled GNSS simulation to their HIL testing environments – a vital requirement in a world where ADAS features are relying more heavily and critically on accurate positioning.”

Spirent has worked with leading suppliers to ensure SimHIL is compatible with their HIL platforms and because of its open API, there’s broad scope for additional custom third-party integrations.

“When used with our GSS7000, SimHIL latency is less than 40ms from motion command to RF output and supports all GNSS and SBAS signals,” said Ricardo Verdeguer Moreno, Product Manager for Connected and Autonomous Vehicles at Spirent. “SimHIL is also compatible with all the options and features available in Spirent’s GNSS simulators, including ionospheric and tropospheric modelling, antenna patterns, date and time settings, and obscuration and multipath effects via Sim3D.”

Users can easily configure and control both the GNSS scenarios, and signal generation and vehicle motion from within the HIL simulator GUI – saving time and the possibility of error.

Spirent is also offering three service packages alongside SimHIL to help customers mitigate project risk and reduce the time from delivery to useful deployment.

For more information about Spirent’s SimHIL integrated testing for Spirent GNSS simulators, visit the SimHIL information page.