This is the CYOBot V2: a modular, transformable robot that you can program with blocks, C++, and Python. It is powered by a ESP32 microcontroller and has Bluetooth, WiFi connectivity. You can quickly assemble it without any soldering. You can change its configuration in a flash.
In the past few years, we have seen a couple of innovative robots that can turn into drones to fly over obstacles and transport items. This 3D printed robot from Michael Rechtin is also worth a look. It shifts from a tank like rover into a quadcopter. As you can see in this video, the robot unfolds its wheels, which hold the rotors it needs to fly around. When on land, it changes its posture to roll around.
This 3D-printed robot can transform from a rover to a drone.
Aerospace engineer Michael Rechtin has created a robot that shifts from a tank-like rover to a quadcopter.
While Michael’s work is a hobby project, universities have been exploring similar designs—like the Morphbot,… pic.twitter.com/pou80mxzCG
— Circuit (@circuitrobotics) November 19, 2024
These features enable this robot to navigate in rough, unpredictable terrain. You can find out more here.
Robots have been used in surgeries for a long time. They are usually teleoperated by surgeons to perform procedures. This surgical robot learned how to perform surgical procedures by watching videos of robotic surgeries. It can get them done with even more precision. As the below video from John Hopkins University shows, this robot was trained using silicone suture pads. Even when disrupted, the robot detects and makes corrections.
Here is an autonomous fleet of robots that can perform tasks faster, with 7x higher success rate. As Figure explains, Figure 02 is now an autonomous fleet to handle end-to-end operations 400% faster. These robots can perform 1000 placements per day. The below video shows them in action.
Robots are going to do many things for us, including cooking our foods and cleaning our plates. Plenty of companies are working on perfecting them. This video from 7X shows their autonomous kitchen robot cleaning 8 dirty mustard plates.
Uncut video of @7Xrobotics autonomous kitchen robot cleaning 8 dirty mustard plates – getting closer to 100% success. Trained on 5.5 hours of video, we’re not throwing a ton of data at a diffusion model like @GoogleDeepMind @physical_int @Tsinghua_Uni but it’s working so far… pic.twitter.com/QhpdWwKL36
— Usman Roshan (@Deeplearner2) November 19, 2024
This robot was trained on 5.5 hours of video. According to the researchers, this robot is getting closer to 100% success rate without relying on a ton of data for a diffusion model.
[HT]
Plenty of researchers are inspired by nature when improving the design of their own robots. Binggwong Leung, Sanislav Gorb, and Poramate Manoonpong have published a paper that explores dung beetle-like robot (ALPHA) with biomechanical feet that can perform adaptive walking and ball rolling tasks on flat and uneven terrains. It can handle different ball types and heights.
As the researchers explain, the modular modular neural-based “contains a central pattern generator (CPG) module, a pattern formation network (PFN) module, and a robot orientation control (ROC) module”
[HT]
This is the UBHOME M10: a smart robotic mower with RTK, AI Vision and LoRa connectivity that can cover up to 7000m2 of lawn every week. It doesn’t require a perimeter wire to work. The M10 has 9 sensors to detect obstacles and get around them. It has an adjustable cutting height of 1.18 to 2.36″. You can use your phone to remote control the robot and manage multiple zones.
This is the SUNSEEKER X7+: a smart robotic mower that you can put to use without using any boundary wires. It uses RTK-GNSS and VSLAM to get around on your property while avoiding obstacles. It has a dual blades for precise cuts. The Orion X7 Plus can cover 1.5 acre of land. It has a cutting width of 14 inches and cutting height of 0.8 to 4 inches.
In the past few years, we have covered plenty of robots that can put out fires while keeping humans safe. They can also be used to seal a fire door with a sealant. This is useful in nuclear facilities where leaks of hazardous materials can pose serious danger to field operators.
Autonomous off-road navigation can be challenging for robots. It requires understanding of conditions and geometric information. RoadRunner M&M is an end-to-end learning-based framework that predicts “the traversability and elevation maps at multiple ranges.” As input, it takes a voxel map and multiple images. Robots using this framework will be able to assess their surroundings in high detail.
According to the researchers, this approach achieves up to 50% better elevation mapping and 30% enhanced traversability estimation over the previous version.
[HT]
