Friday, September 29, 2023

Video Friday: Good Behaviors




Video Friday is your weekly selection of awesome robotics videos, collected by your friends at IEEE Spectrum robotics. We also post a weekly calendar of upcoming robotics events for the next few months. Please send us your events for inclusion.

IROS 2023: 1–5 October 2023, DETROIT
CLAWAR 2023: 2–4 October 2023, FLORIANOPOLIS, BRAZIL
ROSCon 2023: 18–20 October 2023, NEW ORLEANS
Humanoids 2023: 12–14 December 2023, AUSTIN, TEX
Cybathlon Challenges: 02 February 2024, ZURICH, SWITZERLAND

Enjoy today’s videos!

The Toyota Research Institute is unveiling a new approach that allows a robot to acquire new dexterous behaviors from demonstration. We’re going to walk through why this is a critical new capability, what advancements have made this possible, and where we are going next.

[ TRI ]

A low-cost robot does extreme parkour including high jumps on obstacles 2x its height, long jumps across gaps 2x its length, handstand on stairs, and running across tilted ramps.

[ CMU ]

Fourier GR-1, the world’s first mass-produced humanoid robot, is now up for grabs.

[ Fourier Intelligence ]

This robot picking tiny beads from a spinning platform is blowing my mind a little bit.

Towards the goal of realizing next-generation manufacturing, we demonstrate the implementation of made-to-order bead art as a simplified scenario of smart manufacturing. Specifically, by configuring a 3DoF position compensation module which is controlled with 1,000 Hertz visual feedback at the end-effector of an industrial robot arm, the proposed system accurately picks up moving beads on a rotating stage that resembles a belt conveyor and creates bead art according to the design of online orders.

[ Ishikawa Lab ]

Sometimes the Moon doesn’t seem like all that much fun for robots.

[ NASA ]

Server robots have become a common sight in restaurants. The next step is equipping them with robotic arms for enhanced mobile manipulation. In this direction, KIMLAB is partnering with HDHyundai Robotics on MOMO (Mobile Object Manipulation Operator). MOMO features the HDHyundai Robotics B1 as its mobile base, incorporating the adaptable PAPRAS. The system’s primary goals include autonomously clearing floor obstructions and delivering items to humans without human intervention.

[ KIMLAB ]

Blimprobatics!

[ GTSR ]

This work contributes a novel deep navigation policy that enables collision-free flight of aerial robots based on a modular approach exploiting deep collision encoding and reinforcement learning. A set of simulation and experimental studies in diverse environments are conducted and demonstrate the efficiency of the emerged behavior and its resilience in real-life deployments.

[ NTNU ]

Dexterous manipulation has been a long-standing challenge in robotics. While machine learning techniques have shown some promise, results have largely been currently limited to simulation. This can be mostly attributed to the lack of suitable hardware. In this paper, we present LEAP Hand, a low-cost, dexterous, and anthropomorphic hand for machine learning research.

[ CMU ]

During our participation at ARCHE 2023, we are demonstrating telemanipulation capabilities which we have developed at RSL. In the video, you can see the quadruped robot ANYmal (by ANYbotics), a custom robotic arm called DynaArm (by RSL), and a stereo camera system with live streaming capabilities to a 3D screen.

[ RSL ]

Here at Skydio we design, assemble, and support all of our products right here in the United States. Our manufacturing facility in Hayward, California boasts a 37,000 square-foot space and a team of over 100 operators, engineers, technicians, facilities, warehouse operators, planning, and production employees. Our team ensures that we have the current capacity to build and ship hundreds of drones, controllers, and docks to meet the demands of our customers.

[ Skydio ]

There were some good robotics panels at TechCrunch Disrupt this year; here are a couple of them.

[ TC Disrupt ]

Reference: https://ift.tt/UI2bzgw

No comments:

Post a Comment

ChatGPT’s success could have come sooner, says former Google AI researcher

In 2017, eight machine-learning researchers at Google released a groundbreaking research paper called Attention Is All You Need , which in...