Robots are rapidly making their way into a variety of settings, including industrial and manufacturing facilities. So far, they have shown great potential for speeding up and automating a number of manufacturing processes by substituting or assisting human workers on assembly lines. To be adopted on a large scale, however, robots for manufacturing should be both efficient and relatively affordable.
The CYBATHLON 2020 Global Edition is history. Due to the Covid-19 pandemic, the teams had to compete in different time zones and locations. And out of the 50 teams participating, one in four teams were using maxon products.
Robotics researchers at the University of Zurich show how onboard cameras can be used to keep damaged quadcopters in the air and flying stably – even without GPS.
As anxious passengers are often reassured, commercial aircrafts can easily continue to fly even if one of the engines stops working. But for drones with four propellers – also known as quadcopters – the failure of one motor is a bigger problem. With only three rotors working, the drone loses stability and inevitably crashes unless an emergency control strategy sets in.
Researchers at the University of Zurich and the Delft University of Technology have now found a solution to this problem: They show that information from onboard cameras can be used to stabilize the drone and keep it flying autonomously after one rotor suddenly gives out.
Spinning like a ballerina
“When one rotor fails, the drone begins to spin on itself like a ballerina,” explains Davide Scaramuzza, head of the Robotics and Perception Group at UZH and of the Rescue Robotics Grand Challenge at NCCR Robotics, which funded the research. “This high-speed rotational motion causes standard controllers to fail unless the drone has access to very accurate position measurements.” In other words, once it starts spinning, the drone is no longer able to estimate its position in space and eventually crashes.
One way to solve this problem is to provide the drone with a reference position through GPS. But there are many places where GPS signals are unavailable. In their study, the researchers solved this issue for the first time without relying on GPS, instead using visual information from different types of onboard cameras.
Event cameras work well in low light
The researchers equipped their quadcopters with two types of cameras: standard ones, which record images several times per second at a fixed rate, and event cameras, which are based on independent pixels that are only activated when they detect a change in the light that reaches them.
The research team developed algorithms that combine information from the two sensors and use it to track the quadrotor’s position relative to its surroundings. This enables the onboard computer to control the drone as it flies – and spins – with only three rotors. The researchers found that both types of cameras perform well in normal light conditions. “When illumination decreases, however, standard cameras begin to experience motion blur that ultimately disorients the drone and crashes it, whereas event cameras also work well in very low light,” says first author Sihao Sun, a postdoc in Scaramuzza’s lab.
Increased safety to avoid accidents
The problem addressed by this study is a relevant one, because quadcopters are becoming widespread and rotor failure may cause accidents. The researchers believe that this work can improve quadrotor flight safety in all areas where GPS signal is weak or absent.
Supply chains are relying on automation to effectively adapt to fluctuating demand levels, new safety protocols, and shrinking labor pools. The need to operate efficiently, safely, and productively with less people is critical for today and also for success in the future.
An overview of the most popular optimization algorithms for training deep neural networks. From stohastic gradient descent to Adam, AdaBelief and second-order optimization
Researchers from MBARI, the University of Hawai'i at Mānoa (UH Mānoa), and Woods Hole Oceanographic Institution, after years of development and testing, have successfully demonstrated that a fleet of autonomous robots can track and study a moving microbial community in an open-ocean eddy. The results of this research effort were recently published in Science Robotics.
Schools of fish exhibit complex, synchronized behaviors that help them find food, migrate and evade predators. No one fish or team of fish coordinates these movements nor do fish communicate with each other about what to do next. Rather, these collective behaviors emerge from so-called implicit coordination—individual fish making decisions based on what they see their neighbors doing.
Minimally invasive surgeries in which surgeons gain access to internal tissues through natural orifices or small external excisions are common practice in medicine. They are performed for problems as diverse as delivering stents through catheters, treating abdominal complications, and performing transnasal operations at the skull base in patients with neurological conditions.
Robotics researchers at the University of Zurich show how onboard cameras can be used to keep damaged quadcopters in the air and flying stably—even without GPS.
AI is making stunning inroads in the fields of medicine and science. It is helping to cure disease, combat global warming, grow crops and provide cleaner, cheaper energy.
Interesting discussion with Hod Lipson, head of Creative Machines Lab, Columbia University in New York. Can robots be self-aware? Can they design other robots and self-repair? Why should we evolve robots to do tasks that animals do so well? Why don’t we have useful autonomous robots in the real world yet? Find out Hod’s answers to these questions and updates on VoxCAD development for designing and simulation of soft robots in this episode of the IEEE RAS Soft Robotics Podcast.
What’s more, Hod gave his personal advice to roboticists being interviewed for an assistant professorship and to 1st-year robotics PhD students looking for a thesis topic, and he also commented on his approach to the ethical dilemma of military funding scientific research. I hope you enjoy listening to the episode! You can check Hod Lipson’s portfolio here: https://www.hodlipson.com/
Robots have worked in emergency services for decades, and they’re only becoming more prevalent. Here are some leading examples of these machines improving first responders’ response times.
Even though the event is virtual, CES delivers no shortage of big screens or nifty gadgets. But let's be real: both of those are lame compared to the robots.
There is a lot of buzz surrounding industrial analytics, artificial intelligence (AI) and machine learning (ML). However, companies are not limited to taking large and costly decisions when it comes to exploring the possibilities.
Robots that helped people survive and stay safe over the past year are touting their value at the tech industry's annual extravaganza amid a pandemic which has given fresh momentum to the robotics sector.
