<p>➀ MIT engineers have developed a training method for multiagent systems that ensures safe operation in crowded environments. This method can automatically scale to larger groups by training a few agents.</p><p>➁ In real-world tests, small drones successfully switched positions midflight and landed on moving vehicles. Simulations confirmed that the same training, applied to a few drones, could be extended to thousands.</p><p>➂ The method introduces GCBF+, a new approach for ensuring safe navigation in multiagent systems. It simplifies the computation of safety zones by considering an agent’s sensing radius and using simulations to guide agents while maintaining safety.</p>
Related Articles
- New method could monitor corrosion and cracking in a nuclear reactor10 days ago
- “To Build On Our R&D Capabilities, We Provide Customised Drone Development Services”- Rohith Dacharla, Parova Technologies3 months ago
- Beginner's 3D-printed winged VTOL drone can fly for 130 miles — enthusiast with little 3D printing and CAD experience builds long-range drone from scratch3 months ago
- Imec and MIT join forces for non-invasive diagnostic devices4 months ago
- New Chip Checks Cooling For Stacked Electronics4 months ago
- Helping Robots Focus And Lend A Hand4 months ago
- Thin Film May Help Make Light Night-Vision Glasses5 months ago
- AI-Powered Wearable Navigation5 months ago
- World's first drone system for fighting lightning protects cities and infrastructure5 months ago
- UK directed energy weapon defeats drones5 months ago