Caltech engineers revealed a new data-driven method to control the movement of multiple drones through cluttered, unfamiliar spaces, so they do not collide with each other. Obstacles that needed to be overcome in new environments include making split-second decisions about their trajectories despite having incomplete data about their future path and how not to run into one another. Read more for three videos and additional information.
So, the team came up with a multi-robot motion-planning algorithm called “Global-to-Local Safe Autonomy Synthesis” (GLAS) that imitates a complete-information planner with only local information, and “Neural-Swarm,” a swarm-tracking controller augmented to learn complex aerodynamic interactions in close-proximity flight.
- The compact yet powerful Mavic Mini camera drone is the perfect creative companion, capturing your moments in a way that effortlessly elevates the...
- Weighing less than 0.55lbs by 250 grams, Mavic Mini is almost as light as the average smartphone. In the United States and Canada, you can fly this...
- Mavic Mini supports 12MP aerial photos and 2.7K HD videos. A 3-axis motorized gimbal provides superior camera stability and ensures clear,...
Our work shows some promising results to overcome the safety, robustness, and scalability issues of conventional black-box artificial intelligence (AI) approaches for swarm motion planning with GLAS and close-proximity control for multiple drones using Neural-Swarm,” said Soon-Jo Chung, Bren Professor of Aerospace.