Archive 28.11.2023

To best assist humans in real-world settings, robots should be able to continuously acquire useful new skills in dynamic and rapidly changing environments. Currently, however, most robots can only tackle tasks that they have been previously trained on and can only acquire new capabilities after further training.

A new robotic tool developed by a team of experts in computer science and biokinesiology could help stroke survivors more accurately track their recovery progress.

Researchers have developed a self-healing robotic gripper for use in soft robotics that is adaptable, recyclable and resilient to damage, thanks to heat-assisted autonomous healing.

Legged robots that artificially replicate the body structure and movements of animals could efficiently complete missions in a wide range of environments, including various outdoor natural settings. To do so, however, these robots should be able to walk on different terrains, such as soil, sand, grass, and so on, without losing balance, getting stuck or falling over.

To teach an AI agent a new task, like how to open a kitchen cabinet, researchers often use reinforcement learning—a trial-and-error process where the agent is rewarded for taking actions that get it closer to the goal.

A mantra often heard within the manufacturing and logistics industries is that robots are not taking the jobs of humans. And, in many ways, this is true. Today, automation is even a necessary solution to plug a shortage of human labour.

Drawing inspiration from birds, fish and even worms, researchers in Europe are developing machines to explore places on Earth that are difficult for people to reach.

ETH Zurich researchers deployed an autonomous excavator, called HEAP, to build a 6-meter-high and 65-meter-long dry-stone wall. The wall is embedded in a digitally planned and autonomously excavated landscape and park.

It isn't easy for a robot to find its way out of a maze. Picture these machines trying to traverse a kid's playroom to reach the kitchen, with miscellaneous toys scattered across the floor and furniture blocking some potential paths. This messy labyrinth requires the robot to calculate the most optimal journey to its destination, without crashing into any obstacles. What is the bot to do?

The benefits demonstrated by this project underscore the transformative potential of automation in advancing solar construction practices, enabling us to accelerate and de-risk our project pipeline

In recent years, roboticists have introduced increasingly advanced systems, which could open exciting new possibilities for surgery, rehabilitation, and health care assistance. These robotic systems are already helping to improve the quality of life of many people with disabilities, as well as patients who suffered physical trauma or underwent medical procedures.

The easy-to-integrate system consists of a module for robot arms, a computing unit with pre-installed intelligent software and a camera module, each equipped in series with two uEye+ XCP cameras from IDS.

The international media event at Thunderhill Raceway, Willows, CA, marked a first for TRI, offering journalists from the US and Europe an opportunity to ride inside its research vehicles and simulators and experience firsthand how TRI is approaching autonomy.

With 3D inkjet printing systems, engineers can fabricate hybrid structures that have soft and rigid components, like robotic grippers that are strong enough to grasp heavy objects but soft enough to interact safely with humans.

Congratulations to Dautzenberg Roman and his team of researchers, who won the IROS 2023 Best Paper Award on Mobile Manipulation sponsored by OMRON Sinic X Corp. for their paper “A perching and tilting aerial robot for precise and versatile power tool work on vertical walls“. Below, the authors tell us more about their work, the methodology, and what they are planning next.

What is the topic of the research in your paper?

Our paper shows a an aerial robot (think “drone”) which can exert large forces in the horizontal direction, i.e. onto walls. This is a difficult task, as UAVs usually rely on thrust vectoring to apply horizontal forces and thus can only apply small forces before losing control authority. By perching onto walls, our system no longer needs the propulsion to remain at a desired site. Instead we use the propellers to achieve large reaction forces in any direction, also onto walls! Additionally, perching allows extreme precision, as the tool can be moved and re-adjusted, as well as being unaffected by external disturbances such as gusts of wind.

Could you tell us about the implications of your research and why it is an interesting area for study?

Precision, force exertion and mobility are the three (of many) criteria where robots – and those that develop them – make trade-offs. Our research shows that the system we designed can exert large forces precisely with only minimal compromises on mobility. This widens the horizon of conceivable tasks for aerial robots, as well as serving as the next link in automating the chain of tasks need to perform many procedures on construction sites, or on remote, complex or hazardous environments.

Could you explain your methodology?

The main aim of our paper is to characterize the behavior and performance of the system, and comparing the system to other aerial robots. To achieve this, we investigated the perching and tool positioning accuracy, as well as comparing the applicable reaction forces with other systems.

Further, the paper shows the power consumption and rotational velocities of the propellers for the various phases of a typical operation, as well as how certain mechanism of the aerial robot are configured. This allows for a deeper understanding of the characteristics of the aerial robot.

What were your main findings?

Most notably, we show the perching precision to be within +-10cm of a desired location over 30 consecutive attempts and tool positioning to have mm-level accuracy even in a “worst-case” scenario. Power consumption while perching on typical concrete is extremely low and the system is capable of performing various tasks (drilling, screwing) also in quasi-realistic, outdoor scenarios.

What further work are you planning in this area?

Going forward, enhancing the capabilities will be a priority. This relates both to the types of surface manipulations that can be performed, but also the surfaces onto which the system can perch.

---

About the author

Dautzenberg Roman is currently a Masters student at ETH Zürich and Team Leader at AITHON. AITHON is a research project which is transforming into a start-up for aerial construction robotics. They are a core team of 8 engineers, working under the guidance of the Autonomous Systems Lab at ETH Zürich and located at the Innovation Park Switzerland in Dübendorf.