New Technology guides Autonomous Vehicles safely through a highly uncertain environment
MIT researchers have developed a trajectory planning system for autonomous vehicles that allows them to travel from a starting point to a destination location even when there are many different uncertainties in the environment.
The vehicle and the researchers who programmed it don’t know much about this environment. MIT researchers have developed a technique that could help this spacecraft land safely. Their approach can allow an autonomous vehicle to plot a provably safe trajectory in highly unsafe situations, where there are multiple uncertainties about environmental conditions and objects that the vehicle could collide with. The technique could help a vehicle find a safe course around obstacles that move in random ways and change shape over time. It records a safe trajectory to a target region even when the vehicle’s starting point is not known exactly and when it is unclear exactly how the vehicle will move due to environmental factors such as wind, ocean currents or rough terrain.
This is the first technique that allows tackling the problem of trajectory planning with many simultaneous uncertainties and complex safety constraints, says co-lead author Weiqiao Han, a graduate student in the Department of Electrical Engineering and Computer Science and the Computer Science and Artificial Intelligence Laboratory (CSAIL). .
The Researchers evaluated the technology using several simulated navigation scenarios. In one, they modeled an underwater vehicle that plotted a course from an unsafe position around a series of oddly shaped obstacles to a target region. It was able to safely reach the target at least 99 percent of the time.
They also used it to map a safe trajectory for an aircraft that avoided multiple 3D flying objects of uncertain sizes and positions and could move over time while strong winds affected its movement.
With their system, the aircraft reached its target region with a high probability. Depending on the complexity of the environment, the algorithms needed between a few seconds and a few minutes to develop a safe trajectory. Researchers are now working on more efficient procedures that allow for significantly reduced runtimes, which could allow them to get closer to real-time planning scenarios. Researchers are also working on a hardware implementation that would allow the researchers to demonstrate their technique in a real robot.
Newer Articles
- Monkeypox spread in UK: Out of 7 patients found 4 patients are gay or bisexual
- Israeli Company develops AI that will help detect Drowning
- AI to automatically detect and block Cyberattacks
