High-Speed Robot Hand
Channel:Hizook · Length:3:00 · Published:2009-08-03 · Views:4046612
Summary
A short demo from the Ishikawa Komuro Lab of a high-speed robot hand paired with a 1000fps vision system performing dexterous manipulation. It shows what very low-latency vision and actuation can do.
Why HN recommends it
HN cites it as an example of what 1kHz vision and fast control loops enable, in threads about AI hardware and robotics.
Take a look at this video from 2009 demonstrating a 1000fps vision system and a very fast robot hand. — HN, 2016
Robotics · Computer vision, speech & NLP
Subtitles (excerpt)
this video introduces the demonstration of skillful manipulation using a high-speed robotic system the hand module has three fingers a developed small harmonic drive gear and a high power mini actuator are used for each finger link the hand can close the joints at 180° in a tenth of a second the vision system consists of 128x 128 photo detectors and an all pixel parallel processing array using the vision chip enables various image features to be computed within 1 millisecond this tactile sensor is a sheetlike object with only four wires this sensor can measure the center position of a two-dimensional distributed load and the total load within 1 millisecond high-speed control improves not just the speed of existing robot manipulations pursuing the upper limit in terms of speed for mechanical system systems we developed appropriate new control methods for high-speed manipulation this is dribbling high-speed active control enables the maintaining of a periodically stable motion we call it Dynamic holding the dribbling period is around 100 milliseconds this is pen spinning the task is achieved due to the stability of objects experiencing highspeed rotation the contact force and the timing of shifts about the axis of rotation are
On Hacker News
Faster neural nets are essential for robotics. Take a look at this video from 2009 demonstrating a 1000fps vision system and a very fast robot hand. Then compare to recent videos of robots being slow as a turtle. [VIDEO] — visarga, 2016-11
High speed rock paper scissors champ - [LINK] Ishikawa Komuro Labs had a bunch of crazy high speed robotic vision and actuation system ~10 years ago. [VIDEO] if you watch the slow motion there's so much backlash in the system it's hard to believe it works at all, but somehow they factor all of that in. Crazy stuff. That said, for a little side project this is very cool. The simulation idea is dop… — jcims, 2020-03
I think latency makes a lot of difference when an autonomous system is interacting with the world. Take a look at this video from 2009 where they use a high speed vision system (1000fps!). The things it could do are probably unequaled even today. [VIDEO] The higher the speed of the system, the less it has to predict in the future and better can adapt to unforeseen situations. It's basically using… — visarga, 2018-08
I am watching AI papers and YouTube demonstrations of robotics and it seems they stagnate. It's frustrating to see it takes 2 minutes for a robotic hand to open a door in this day. What happened to fast vision systems? Here's a 2009 video of a high speed robotic hand and vision system. It does 1000fps: [VIDEO] Why hasn't anyone surpassed it since 2009? — visarga, 2016-11
Won't get anywhere with a dataset. You need dozens or hundreds of them, and they are usually created using Amazon Turk, so anyone with some money can create one. And they need to be commissioned by the AI researchers, because they know best what they want to study. NVIDIA needs to become more efficient and build deep learning hardware instead of graphics cards that do faster computation than CPU.… — visarga, 2016-11
Related videos
- RL Course by David Silver - Lecture 1: Introduction to Reinforcement Learning · Google DeepMind · 1:28:12
- Why Greatness Cannot Be Planned — Kenneth Stanley · Machine Learning Street Talk · 2:46:27
- Neural Network Learns The Physics of Fluids and Smoke | Two Minute Papers #118 · Two Minute Papers · 5:26
- Attention Is All You Need · Yannic Kilcher · 27:06
- RAAIS 2017 - Simon Knowles, Co-Founder and CTO of Graphcore · The Research and Applied AI Summit - RAAIS · 35:44
- What Happened to Horses Is Happening to Us · CGP Grey · 15:00
- Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning · Google TechTalks · 48:10
- "Voice Driven Development: Who needs a keyboard anyway?" by Emily Shea · Strange Loop Conference · 41:17
- Andrej Karpathy - AI for Full-Self Driving at Tesla · Matroid · 30:08
- Tensorflow and deep learning - without a PhD by Martin Görner · Devoxx · 2:35:53
- JPEG DCT, Discrete Cosine Transform (JPEG Pt2)- Computerphile · Computerphile · 15:11
- Fourier Optics used for Optical Pattern Recognition · Huygens Optics · 18:30
- Zipline - How Rwanda Built A Drone Delivery Service · Real Engineering · 11:45
- Let's build the GPT Tokenizer · Andrej Karpathy · 2:13:34
- Massive-scale online collaboration | Luis von Ahn · TED · 16:40
- Amazing Invention- This Drone Will Change Everything · Mark Rober · 21:32