Video Friday is your weekly collection of superior robotics movies, collected by your pals at IEEE Spectrum robotics. We additionally submit a weekly calendar of upcoming robotics occasions for the subsequent few months. Please ship us your occasions for inclusion.
Humanoids 2023: 12–14 December 2023, AUSTIN, TEX.
Cybathlon Challenges: 02 February 2024, ZURICH, SWITZERLAND
Eurobot Open 2024: 8–11 Could 2024, LA ROCHE-SUR-YON, FRANCE
Take pleasure in at present’s movies!
Do you end up questioning why the world wants bipedal humanoid robots? Enable IHMC and Boardwalk Robotics to reply that query with this video.
[ IHMC ]
Thanks, Robert!
As NASA’s Ingenuity Helicopter made its 59th flight on Mars–reaching its second highest altitude whereas taking footage of this flight–the Perseverance Mars rover was watching. See two views of this 142-second flight that reached an altitude of 20 meters (66 toes). This flight came about on 16 Sept. 2023. On this side-by-side video, you’ll see the angle from Perseverance on the left, which was captured by the rover’s Mastcam-Z imager from about 55 m (180 ft.) away. On the suitable, you’ll see the angle from Ingenuity, which was taken by its downward-pointing Navigation Digital camera (Navcam). Throughout Flight 59, Ingenuity hovered at totally different altitudes to examine Martian wind patterns. The very best altitude achieved on this flight was 20 m. On the time, that was a file for the helicopter.
[ JPL ]
Cassie Blue showcases its means to navigate a transferring walkway, a standard but difficult state of affairs in human environments. Cassie Blue can stroll on to and off of a 1.2 meter-per-second transferring treadmill and reject disturbances attributable to a tugging gantry and sub-optimal strategy angle attributable to operator error. The important thing to Cassie Blue’s success is a brand new controller that includes a novel mixture of digital constraint-based management and a mannequin predictive controller utilized on the often-neglected ankle motor. This know-how paves the way in which for robots to adapt and performance in dynamic, real-world settings.
[ Paper ] by way of [ Michigan Robotics ]
Thanks, Wami!
On this examine, we suggest a parallel wire-driven leg construction, which has one DoF of linear movement and two DoFs of rotation and is managed by six wires, as a construction that may obtain each steady leaping and excessive leaping. The proposed construction can concurrently obtain excessive controllability on every DoF, lengthy acceleration distance and excessive energy required for leaping. In an effort to confirm the leaping efficiency of the parallel wire-driven leg construction, we’ve got developed a parallel wire-driven monopedal robotic, RAMIEL. RAMIEL is supplied with quasi-direct drive, excessive energy wire winding mechanisms and a light-weight leg, and might obtain a most leaping top of 1.6 m and a most of seven steady jumps.
[ RAMIEL ]
Thanks, Temma!
PAL Robotics’ Kangaroo demonstrates traditional “zero-moment level” or ZMP strolling, with just one or two engineers tagging alongside, and neither of them look all that nervous.
Ultimately, PAL Robotics says that the robotic will be capable to “carry out agile maneuvers like working, leaping, and withstanding impacts.”
[ PAL Robotics ]
Thanks, Lorna!
SLOT is a small soft-bodied crawling robotic with electromagnetic legs and passive physique adaptation. The robotic, pushed by neural central sample generator (CPG)-based management, can efficiently crawl on quite a lot of steel terrains, together with a flat floor, step, slope, confined area, and an interior (concave floor) and outer (convex floor) pipe in each horizontal and vertical instructions. It may be additionally steered to navigate by a cluttered atmosphere with obstacles. This small tender robotic has the potential to be employed as a robotic system for interior and outer pipe inspection and confined area exploration within the oil and fuel trade.
[ VISTEC ]
Thanks, Poramate!
It isn’t straightforward for a robotic to seek out its means out of a maze. Image these machines making an attempt to traverse a child’s playroom to succeed in the kitchen, with miscellaneous toys scattered throughout the ground and furnishings blocking some potential paths. This messy labyrinth requires the robotic to calculate probably the most optimum journey to its vacation spot, with out crashing into any obstacles. What’s the bot to do? MIT CSAIL researchers’ “Graphs of Convex Units (GCS) Trajectory Optimization” algorithm presents a scalable, collision-free movement planning system for these robotic navigational wants.
[ MIT CSAIL ]
As the sector of human-robot collaboration continues to develop and autonomous general-purpose service robots turn out to be extra prevalent, robots have to receive situational consciousness and deal with duties with a restricted area of view and workspace. Addressing these challenges, KIMLAB and Prof. Yong Jae Lee on the College of Wisconsin-Madison make the most of the sport of chess as a testbed, using a general-purpose robotic arm.
[ KIMLAB ]
Humanoid robots have the potential of turning into basic objective robots augmenting the human workforce in industries. Nonetheless, they have to match the agility and flexibility of people. On this paper, we carry out experimental investigations on the dynamic strolling capabilities of a series-parallel hybrid humanoid named RH5. We exhibit that it’s potential to stroll as much as speeds of 0.43 m/s with a position-controlled robotic with out full state suggestions, which makes it one of many quickest strolling humanoids with related dimension and actuation modalities.
[ DFKI ]
Avocado drone. That’s all.
[ Paper ]
Autonomous robots should navigate reliably in unknown environments even underneath compromised exteroceptive notion, or notion failures. Such failures typically happen when harsh environments result in degraded sensing, or when the notion algorithm misinterprets the scene as a consequence of restricted generalization. On this paper, we mannequin notion failures as invisible obstacles and pits, and practice a reinforcement studying (RL) based mostly native navigation coverage to information our legged robotic.
X20 Lengthy Vary Distant Hazard Detection Check. We distant the robotic canine from a straight line distance of 1 kilometer, and it efficiently examined the density of gases. The aim of the check is to offer resolution for firefighters to make use of the robotic to detect dangerous gases first earlier than placing themselves in peril.
[ Deep Robotics ]
This CMU RI Seminar is by Robert Ambrose from Texas A&M, on “Robots on the Johnson Area Heart and Future Plans.”
The seminar will assessment a sequence of robotic methods constructed on the Johnson Area Heart over the past 20 years. These will embody wearable robots (exoskeletons, powered gloves and jetpacks), manipulation methods (ISS cranes right down to human scale) and lunar mobility methods (human floor mobility and robotic rovers). As all robotics shows ought to, it will embody some enjoyable movies.
[ CMU RI ]