MIT researchers have developed an AI-based method to improve safety and stability in autonomous robots, successfully addressing the ‘stabilize-avoid’ problem. Using a two-step approach involving deep reinforcement learning and mathematical optimization, the method was effectively tested on a simulated jet aircraft. This could have future applications in dynamic robots requiring safety and stability, like autonomous delivery drones.
In an experiment that would make Maverick proud, their technique effectively piloted a simulated jet aircraft through a narrow corridor without crashing into the ground. The MIT researchers broke the problem down into two steps. First, they reframe the stabilize-avoid problem as a constrained optimization problem. In this setup, solving the optimization enables the agent to reach and stabilize to its goal, meaning it stays within a certain region. By applying constraints, they ensure the agent avoids obstacles, So explains.
When compared with several baselines, their approach was the only one that could stabilize all trajectories while maintaining safety. To push their method even further, they used it to fly a simulated jet aircraft in a scenario one might see in a “Top Gun” movie. The jet had to stabilize to a target near the ground while maintaining a very low altitude and staying within a narrow flight corridor.