{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Futurism Tech Brief By HackerNoon","title":"MIT’s VLASH System Lets Robots Plan While They Move","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/2897db69\"></iframe>","width":"100%","height":180,"duration":195,"description":"\n        This story was originally published on HackerNoon at: https://hackernoon.com/mits-vlash-system-lets-robots-plan-while-they-move.\nMIT's VLASH lets robots plan ahead while moving, cutting the pauses behind jerky motion and roughly doubling task speed.\nCheck more stories related to futurism at: https://hackernoon.com/c/futurism.\n            You can also check exclusive content about #robotics, #mit, #vlash, #news, #tech-innovations, #innovative-robotic, #mit-robotics, #service-robots,  and more.\nThis story was written by: @quinnhillerich. Learn more about this writer by checking @quinnhillerich's about page,\n            and for more stories, please visit hackernoon.com.\nMIT researchers built VLASH, a system that lets robots plan their next move while still executing the current one, instead of stopping to replan. It roughly doubles speed on pick-and-place tasks and shows bigger gains on fast, continuous tasks like table tennis and Whack-a-Mole, with no added compute cost or special hardware needed. A companion technique, action quantization, pushes speed further (1.5–2x) at a small accuracy cost. It's not a fix for every scenario, unpredictable or contact-heavy environments still need more testing, but it targets a bottleneck that's slowed robots down for years.","thumbnail_url":"https://img.transistorcdn.com/dkSY09WMT3S7SiI_n-P5daFmTJplJgc8AfjEgyM1Kqg/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9zaG93/LzQxMjcwLzE2ODM1/ODI1MTQtYXJ0d29y/ay5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}