Sari la conținut

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

perspectiva aiqbenchCipuri & infrastructură

analiza aiqbench

This research demonstrates how algorithm-hardware co-design enables ultra-low-power 3D mapping for autonomous micro-robots, solving the critical energy bottleneck that currently limits their deployment in complex environments. By reducing power consumption to levels comparable to a single LED while maintaining high-fidelity spatial awareness, this system-on-a-chip paves the way for scalable swarms of tiny UAVs and extended-wear augmented reality devices.
Surse care acoperăMIT News, Viakoo, Quantum Zeitgeist
Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

New chip could help tiny robots traverse complex environments

MIT News7 min de cititArticolul și perspectiva sunt în engleză.

Researchers combined an efficient algorithm with dedicated hardware to rapidly generate 3D maps for navigation using minimal memory and power.

A new chip developed by MIT researchers could help tiny, low-power UAVs avoid obstacles as they zip around tight corners inside an industrial HVAC system to check for gas leaks. The chip allows small autonomous robots and other battery-limited devices to construct detailed 3D maps of their environments in real-time using only about as much power as a single LED. A robot could use such a map to plan a collision-free path to reach its goal. Typically, generating such thorough maps requires power-hungry systems and a great deal of memory to build and store 3D representations of the obstacles in a robot’s environment. The MIT researchers took a different approach by combining an extremely efficient mapping algorithm with specialized hardware designed to accelerate its workload, which minimizes memory…

Extras afișat conform termenilor RSS ai publicației · 128 cuvinte · textul integral și figurile sunt pe site-ul publicației

Subiecte conexe