Video Friday: Humanoid Robot Digit Takes a Stroll Downtown
HiBot, the Japanese company best known for its versatile snakebots, is developing a new robotic platform that is less snake-y but still highly capable of making its way into hard-to-reach areas. Called FloatArm, it’s designed to inspect spaces in and around large pieces of equipment and other infrastructure. The current version is slightly longer than 2 meters but the production version the company plans to introduce soon will be 5 m. “You can control it with a gamepad but the system also has some semi-autonomous and completely autonomous behaviors,” says HiBot CEO Michele Guarnieri.
[ HiBot ]
Digit gets some outdoor exercise, testing battery and motor endurance.
[ Agility Robotics ]
Something to do with your Jibo if you have a robot arm that needs a face:
That robot is DRAWING ON KITKATS WITH FROSTING.
[ TOPPI ]
The ROAHM (Robotics and Optimization for the Analysis of Human Motion) Lab at the University of Michigan presents a highlight video for their Dynamic Walking poster:
“Predicts how long I’ll need to walk again” is going to be stuck in my head. All. Day.
[ ROAHM Lab ]
Lukas Kaul, a postdoc at the Karlsruhe Institute of Technology, writes in to share this open-source self-balancing robot that he built as a side project. Called HoverBot, it’s based on off-the-shelf parts, and the software and instructions are all on GitHub. In the video below, shot and edited by Felix von Drigalski, they take HoverBot for a spin at a skate park.
While the robot design is pretty straight-forward, I think it stands out amongst most other self-balancing robot projects in terms of outdoor performance and ruggedness. The video is supposed to be an entertaining showcase of this.
The design, control scheme, software, mechanical components and instructions are intentionally kept very simple to enable anyone with a bit of tinkering experience to build their own and hopefully learn and have fun along the way.
[ GitHub ]
For environmental monitoring, precision agriculture, infrastructure maintenance and certain security applications, slow and energy efficient can be better than fast and always needing a recharge. That’s where “SlothBot” comes in. Powered by a pair of photovoltaic panels and designed to linger in the forest canopy continuously for months, SlothBot moves only when it must to measure environmental changes.
Slothbot is my spirit robot.
[ Georgia Tech ]
At Caltech’s Center for Autonomous Systems and Technologies (CAST), artificial intelligence experts have teamed up with control experts to develop a system that uses a deep neural network to help autonomous drones “learn” how to land more safely and quickly, while gobbling up less power. The system they have created, dubbed the “Neural Lander,” is a learning-based controller that tracks the position and speed of the drone, and modifies its landing trajectory and rotor speed accordingly to achieve the smoothest possible landing.
[ Caltech ]
Why worry about an optimal gripper design, when you can just use your grippers to grip other grippers for grippier gripping?
This work designs a mechanical tool for robots with 2-finger parallel grippers. It extends the function of the robotic gripper without additional requirements on tool exchangers or other actuators. The tool is general and does not require power or air supply. It could be used by any robots with 2-finger parallel grippers.
Over the years, people were developing tools for human hands. This work is developing tools for intelligent robots! It demonstrates intelligent robots can use the tool through vision and planning in narrow work spaces where they cannot reach using their hands.
[ Paper ]
The laws of physics may say it’s near impossible to fly on Mars, but actually flying a heavier-than-air vehicle on the Red Planet is much harder than that. NASA’s Mars 2020 mission will deliver a technology demonstration that will put the idea to the test — a helicopter that will perform controlled flight on Mars.
[ JPL ]
Here’s a clever way of simplifying soft robots: Program motion into their design by using tubes that transfer air between sections at different rates.
Watch this rotor wing aircraft transition from spinning hover mode to flight mode:
[ SUTD ]
Pepper is five years old! And SoftBank would like to remind you that Pepper is a pretty good research platform. And also a boy.
[ SoftBank ]
Here are two different robotic systems designed for picking berries. The first is from Fieldwork Robotics:
And the second is from Traptic:
QMI Robotics is developing grippers for collaborative robots powered by miniature hydraulics, which allows it to lift very heavy objects (as well as delicate ones).
[ QMI Robotics ]
This video shows our humanoid robot Lola walking on asphalt, grass, and cobblestone. All motions were generated online and on board of the robot. The cable is needed for power supply as the robot doesn’t have a battery yet. Lola is safeguarded by a safety harness – this rope is loose during walking.
For this video, Lola was either operated by a human via a wireless controller or commanded simple objectives, e.g. “walk straight”. The motion planner assumes a flat ground and the different ground properties are previously unknown to the robot’s feedback control methods.
[ TUM ]
The ExoMars mission will see Rosalind Franklin the rover and its surface platform Kazachok land on the Red Planet in 2021. From fine-grained soil to large boulders and slopes, the rover has to be able to move across many types of terrain, collect samples with a 2 m-long drill and analyse them with instruments in its onboard laboratory.
[ ESA ]
X (you know, the Google place) wants you to do robotics!
[ X ]
Highlights from the RoboCup German Open. This is the standard platform league (playing with Nao robots), so prepare your expectations accordingly.
[ B-Human ]
Robots in Depth is back! In this episode, Per interviews Andreas Bihlmaier from Robodev, which makes modular robots.
Andreas shares how he started out in computers and later felt that robotics, through its combination of software and hardware that interacts with the world, was what he found most interesting.
Andreas is one of the founders of RoboDev, a company that aims to make automation more available using modular robotics. He explains how modular systems are especially well suited for automating low volume series and how they work with customers to simplify automation.
He also discusses how a system that can easily be assembled into many different robots creates an advantage both in education and in industrial automation, by providing efficiency, flexibility and speed.
[ Robots in Depth ]