A 3D-Powered Bid to Test Out Your Autonomous Vehicles

Human beings, like we know, tend to have many notable qualities, but to be completely honest, none defines us better than that tendency of growing on a consistent basis. This progressive tendency, in particular, has brought the world some pretty huge milestones, with technology emerging as a major member of the stated group. The reason why we hold technology in such a high regard is, by and large, predicated upon its skill-set, which ushered us towards a reality that nobody could have ever imagined otherwise. Nevertheless, if we look beyond the surface for a second, it will become clear how the whole runner was also very much inspired from the way we applied those skills across a real world environment. The latter component was, in fact, what gave the creation a spectrum-wide presence, and consequentially, kickstarted a full-blown tech revolution. Of course, this revolution then went on to scale up the human experience from various different directions, but even after achieving a feat so notable, technology will somehow continue to bring out the right goods. The same has turned more and more evident in recent times, and assuming one new discovery pans out just like we envision, it will only put that trend on a higher pedestal moving forward.

Southwest Research Institute (SwRI) has successfully created a 3D simulation tool to test automated vehicles in virtual off-road environments modeled after real-world conditions. Under the development, the researchers conceived a “Simulation Scene Adjustment Tool” with a 3D video game-style interface to test virtual ground vehicles on off-road terrain. Talk about this simulator, it is made from a graphics engine, dynamics engine, vehicle modeling tools, vehicle terrain interaction models, and plug-ins to communicate with an autonomy software stack. To build out scenes, the technology leverages elevation maps captured from geographic information system (GIS) data and graphically renders topographical features in 3D. Going by the available details, the first round of research incorporated digital elevation models (DEMs) from aerial scans conducted by the San Antonio River Authority and other government agencies. As far as perceiving scene objects, movements, and position when calculating driving responses is concerned, though, the machine learning algorithms, used to manufacture the simulator, actively replicate computer vision and sensing outputs for lidar, radar, cameras, GPS, and other systems.

“We developed algorithms to perturb DEM and GIS data in user-configurable ways that generate synthetic environments,” said. Joe Auchter, an engineer who led the research for SwRI’s Intelligent Systems Division. “This allows for testing of new algorithms and techniques in simulation, building numerous test environments that share certain relevant characteristics with a real geo-specific location where vehicles will eventually operate.”

Another detail worth a mention here is how simulated vehicles here can also be programmed with particular weight, speed, horsepower, center of gravity, and other such elements, thus ensuring that we get the most relevant brand of results.

Interestingly, the development in focus follows up on U.S. Department of Defense’s growing demand for modeling and simulation tools so to ensure the development of unmanned ground vehicles (UGVs), the military term for automated or autonomous vehicles. Now, given it is to be used for both military and civilian purposes, the researchers have also allotted a serious amount of attention towards shoring up their system’s security.

“If you look at field testing of automated vehicles, there are simply not enough miles or novel situations that you can throw at a vehicle to encounter all the edge cases for sensors and software,” said Jerry Towler, assistant director of Southwest Research Institute’s Robotics Department. “Modeling and simulation help test AVs and Advanced Driver Assistance Systems (ADAS) to enhance safety and ensure capability before and alongside deployment into real-world testing environments.”

Copyrights © 2024. All Right Reserved. Engineers Outlook.