Video Friday: Punch-Out – IEEE Spectrum

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

Humanoids 2023: 12-14 December 2023, AUSTIN, TEX.
Cybathlon Challenges: February 2, 2024, ZURICH, SWITZERLAND
Eurobot Open 2024: 8-11 May 2024, LA ROCHE-SUR-YON, FRANCE

Have fun with today's videos!

Are you wondering why the world needs bipedal humanoid robots? Allow IHMC and Boardwalk Robotics to answer this question with this video.

[ IHMC ]

Thanks, Robert!

As NASA's Ingenuity Helicopter completed its 59th flight on Mars, reaching its second-highest altitude while taking photos of the flight, the Mars rover Perseverance observed the action. See two perspectives of this 142-second flight, which reached a height of 20 meters (66 feet). This flight took place on September 16, 2023. In this side-by-side video, you can see Perseverance's perspective on the left, captured by the rover's Mastcam-Z imager from about 55 m (180 feet). away. On the right is Ingenuity's perspective taken with the downward-facing navigation camera (Navcam). During Flight 59, Ingenuity hovered at various altitudes to check Mars' wind patterns. The highest flight altitude reached was 20 m. That was a record for the helicopter at the time.

[ JPL ]

Cassie Blue demonstrates his ability to navigate a treadmill, a common but challenging scenario in human environments. Cassie Blue can ascend and descend onto a treadmill moving at 1.2 meters per second and suppress interference from a pulling gantry and a suboptimal approach angle caused by operator error. Key to Cassie Blue's success is a new controller with a novel combination of virtual constraint-based control and a model predictive controller applied to the often neglected ankle motor skills. This technology paves the way for robots to adapt and function in dynamic, real-world environments.

[ Paper ] above [ Michigan Robotics ]

Thanks, Wami!

In this study, we propose a parallel wire-driven leg structure that has one DoF of linear motion and two DoFs of rotation and is controlled by six wires as a structure that can achieve both continuous jumping and high jumping. The proposed structure can simultaneously achieve high controllability in any DoF, long acceleration distance and high power required for jumping. To verify the jumping performance of the parallel wire-driven leg structure, we developed a parallel wire-driven monopedal robot, RAMIEL. Equipped with quasi-direct drive, powerful wire wrapping mechanisms and a lightweight leg, RAMIEL can reach a maximum jump height of 1.6m and a maximum of seven continuous jumps.


Thank you, Temma!

PAL Robotics' Kangaroo was designed to be lightweight and powerful, allowing the robot to perform agile maneuvers. To achieve this, we analyzed existing bipedal platforms and developed a novel leg design based on ball screw linear actuators and closed kinematic chains. However, the team faced a challenge as there are few control algorithms and libraries that support closed kinematic chains. To overcome this challenge, we defined the full model of the robot and implemented a library that calculates all transformations using virtual constraints. and defined a simple model and integrated all nonlinear transformations into the ROS transmissions. Using these approaches, here we demonstrate kangaroo walking using a zero moment point (ZMP)-based position control algorithm.

[ PAL Robotics ]

Thank you, Lorna!

SLOT is a small crawling robot with a soft body, electromagnetic legs and passive body adjustment. The robot, powered by a neural central pattern generator (CPG)-based controller, can successfully crawl on a variety of metal surfaces, including a flat surface, a step, a slope, a narrow space, as well as an interior (concave surface) and exterior ( convex surface). ) pipe in both horizontal and vertical directions. It can also be controlled to navigate through a confusing environment with obstacles. This small soft robot has the potential to be used as a robotic system for internal and external pipe inspection and confined space exploration in the oil and gas industry.


Thank you, Poramate!

It's not easy for a robot to find its way out of a maze. Imagine these machines trying to cross a child's playroom to reach the kitchen, while various toys are scattered on the floor and furniture blocks some potential paths. This chaotic maze requires the robot to calculate the optimal route to its destination without hitting any obstacles. What should the bot do? MIT CSAIL researchers' Graphs of Convex Sets (GCS) Trajectory Optimization algorithm presents a scalable, collision-free motion planning system for these robot navigation needs.


As the field of human-robot collaboration continues to grow and general-purpose autonomous service robots become more common, robots will need to acquire situational awareness and perform tasks with a limited field of view and workspace. To address these challenges, KIMLAB and Prof. Yong Jae Lee of the University of Wisconsin-Madison are using chess as a testbed using a general-purpose robotic arm.


Humanoid robots have the potential to become general-purpose robots that complement the human workforce in industry. However, they must correspond to the agility and versatility of humans. In this paper, we conduct experimental studies on the dynamic walking capabilities of a serial-parallel hybrid humanoid named RH5. We show that it is possible to achieve speeds of up to 0.43 m/s with a position-controlled robot without full state feedback, making it one of the fastest walking humanoids with similar size and actuation modalities.

[ DFKI ]

Avocado drone. That's all.

[ Paper ]

Autonomous robots must navigate reliably in unknown environments even with limited exteroceptive perception or perception errors. Such errors often occur when harsh environments lead to impaired perception or when the perception algorithm misinterprets the scene due to limited generalization. In this paper, we model perceptual errors as invisible obstacles and pits and train a reinforcement learning (RL)-based local navigation policy to guide our legged robot.

[ Resilient Navigation ]

X20 Long Range Remote Hazard Detection Test. We removed the robot dog from a distance of one kilometer as the crow flies and it successfully tested the density of gases. The purpose of the test is to provide a solution for firefighters to use the robot to first detect harmful gases before putting themselves in danger.

[ Deep Robotics ]

This CMU RI seminar is from Robert Ambrose of Texas A&M on “Robots at Johnson Space Center and Future Plans.”

The seminar will discuss a number of robotic systems built at Johnson Space Center over the past 20 years. These include wearable robots (exoskeletons, powered gloves and jetpacks), manipulation systems (human-scale ISS cranes) and lunar mobility systems (human surface mobility and robotic rovers). As with all robotics presentations, there will be some entertaining videos included.

[ CMU RI ]

You might also like

Comments are closed.