<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
- Tabletop factory-in-a-box makes hands-on manufacturing education more accessible4 months ago
- Engineers develop a way to mass manufacture nanoparticles that deliver cancer drugs directly to tumors4 months ago
- Cem Tasan to lead the Materials Research Laboratory4 months ago
- Mapping the future of metamaterials4 months ago
- 3D Printing Cable-Driven Robots With Precision4 months ago
- Artificial muscle flexes in multiple directions, offering a path to soft, wiggly robots4 months ago
- Chip-Based System To Generate Terahertz Waves5 months ago
- DSTL experiments with robotic dogs for bomb disposal5 months ago
- Pb-free thermistors for battery packs and drones5 months ago
- Breakthrough In Magic-Angle Graphene Research5 months ago