This is the BRINC Responder: a drone platform designed to improve situational awareness for first responders. This drone comes with a full HD 40x zoom camera and 640px thermal sensor, so firefighters can use it to identify hot spots. The Responder Station is a robotic charging station that keeps these drones ready to go. Drones can be deployed under 5 seconds.
In the past few years, we have covered plenty of clever drone perching mechanism. Researchers have now developed a bioinspired drone foot that allows for passive dynamic perching. Their solution uses soft tendons to link the the motion of an ankle linkage and the claws. It uses “an electroadhesive locking mechanism attached to the tendon locks the claws within 20 ms after reaching closed configuration.”
Meet the AgileX Robotics Ranger Mini 3.0: a versatile mobile robot with omnidirectional movement that can operate in challenging conditions. It can adapt to uneven terrain. It operates in low and high temperature conditions. This robot has a 8-hour battery with 35km range. It features IP54 rating. It weighs 120kg.
Python is one of the most important programming languages around these days. It has applications in AI, robotics, data science, and other fields. Teaching it to kids doesn’t have to be boring. This Ping Pong Launcher Coding Kit comes with everything your kids need to learn Python while having fun. Students have access to online tutorials that show them how to write Python code.
Drones are used for a wide variety of tasks. Most of them have a limited range, so they require charging mid-mission. Researchers have now come up with a fully autonomous self-recharging drone system. This drone has a vision and navigation system to locate powerlines to land on them. Here is how it works:
A passively actuated gripping mechanism grasps the powerline cable during landing after which a control circuit regulates the magnetic field inside a split-core current transformer to provide sufficient holding force as well as battery recharging.
This approach allows drones to take on longer missions without major interruptions.
[HT]
Teaching robots how to slice food ingredients is easier said than done. SliceIt! is a simulation based approach for training food slicing skills. The approach consists of:
collecting a small dataset of real food-cutting examples, then calibrating high-fidelity simulations of knife-food cutting interactions and robot motion control. Reinforcement learning agents are trained in this calibrated simulation environment to learn optimal compliance control policies that modulate knife forces.
Once the info is transferred to the robot, it will be able to perform food slicing tasks efficiently and safely.
[HT]
Here is a robot inspired by the movements of a snail that can climb walls. It was made by researchers at the University of Bristol. They used a slicing suction approach to pull this off. This robot can carry 1kg of mass. It can slide vertically and upside down.
Robots are already capable of operating coffee machines. The Cafe Robot takes it to the next level by leveraging the power of LLMs. It can scoop, pour liquid and perform other tasks required to make coffee. As the researchers explain, this robot makes coffees and cakes by using AI based skills.
dialogue for making coffee, as well as the coordination of each action based on the dialogue, is facilitated by the Integral Task Planner
The below video shows it in action:
[HT: Jad Tarifi, Nima Asgharbeygi, Shuhei Takamatsu, Masataka Goto]
Robots have been used for surgeries for a long time. Sony has developed a new robot that offers assistance with microsurgeries. It is designed to work on veins and nerves. It uses a highly sensitive control device to capture the movements the surgeon’s hands and fingers and replicate them.
This robotic system has a compact system to store surgical instruments that its robot arm can exchange without human intervention. This prototype has 1.3-type 4K OLED Microdisplays.
[HT]
This is the ArrayBot: a distributed manipulation system on a 16 x 16 array of sliding pillars with tactile sensors that can manipulate and support objects on a table. Researchers used reinforcement learning algorithms to pull this off. As they explain:
“we train RL agents that can relocate diverse objects through tactile observations only… Surprisingly, we find that the discovered policy can not only generalize to unseen object shapes in the simulator but also transfer to the physical robot without any domain randomization.”
![[ICRA2024] ArrayBot: Reinforcement Learning for Generalizable Distributed Manipulation through Touch](https://www.roboticgizmos.com/wp-content/plugins/wp-youtube-lyte/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FvhhCsG38Nvw%2F0.jpg)
Such an approach can be used to relocate two melons in parallel, relocate a dragon fruit, and a lot more.
