AB Dynamics has presented ClearTrack, a fully integrated object detection system for driverless robot-controlled vehicle testing, developed with sister company ABD Solutions. ClearTrack enables automotive manufacturers to scale-up their driverless durability, misuse and mileage accumulation testing operations by automating obstacle detection and avoidance, maximizing uptime and optimizing test schedules. It also provides an extra layer of protection for valuable assets by helping to prevent impacts with obstacles on the track, such as animals or large debris.
“Using robots to remove the driver from repetitive and often arduous testing has a host of benefits not just for personnel, but also improving the cost and efficiency of testing,” said Jonathan Barry, senior embedded and control software engineer at AB Dynamics. “ClearTrack amplifies these benefits. Our fully integrated active object detection system helps protect valuable prototypes from damage and can enable more vehicles to operate simultaneously on the same track.”
ClearTrack is designed to integrate with AB Dynamics’ driverless solution. Its core component is a high-resolution, solid-state, ultra-long-range (500m) lidar sensor developed for autonomous applications. The system also includes an in-house-developed perception ECU and a roof-mounting assembly. It connects to the driverless vehicle’s controller unit and is operated through the AB Dynamics robot controller software interface.
The solution utilizes robots, software, telemetry and controllers to accurately control a vehicle’s speed and direction. Under normal driving conditions, the solution typically enables vehicles to follow a predetermined path to within 2cm, speed to within 0.5km/h and steering angle to within 0.5 degrees.
The detection system calculates the size, shape, position and direction of obstacles in real time and performs an immediate abort stop to prevent an impact if an obstacle poses a collision risk. ClearTrack can be finely tuned to filter out obstacles that don’t pose a risk of damage to the vehicle, such as low-lying or sparse foliage. Its configurable settings allow the user to control the sensitivity of the system depending on its operational environment. This includes object height filters for test areas that include tunnels or bridges, helping to keep testing efficient without compromising safety.
The solution has been designed for fast and simple deployment and is compatible with almost any vehicle. Capable of test speeds up to 130km/h, it is also built for the demands of durability testing, including rough and uneven terrain. Motion compensation technology corrects the smearing of lidar points when the vehicle is moving.
“ClearTrack allows OEMs to scale their driverless operations safely and efficiently,” Barry continued. “By providing an additional layer of information and enhanced situational awareness, an operator’s workload is significantly reduced. As a result, they can comfortably and safely monitor and control more vehicles.”
In related news, Gatik has launched Arena, its next-generation simulation platform designed to accelerate the development and validation of autonomous vehicle systems. The platform has been developed in collaboration with Nvidia and integrates Nvidia Cosmos World Foundation Models (WFMs)