Creating a robotic wheelchairs that is user-friendly for crowds

robotic wheelchair

robotic wheelchair

In the near future, crowds may be easily and safely navigated by robotic wheelchairs. Researchers from EPFL are investigating the technical, ethical, and safety challenges associated with this type of technology as part of CrowdBot, an EU-funded project. The project’s ultimate goal is to make it easier for people with disabilities to move around.

Shoppers at Lausanne’s weekly outdoor market may have come across one of EPFL’s inventions in the past few weeks—a newfangled device that’s part wheelchair, part robot. It’s being used by researchers at EPFL’s Learning Algorithms and Systems Laboratory (LASA) to test technology they’re developing under CrowdBot, a project led by INRIA and involving a consortium of seven research organizations, including EPFL.

The project has received funding from the EU’s Horizon 2020 program in the Information and Communication Technology (ICT) section. CrowdBot aims to test the technical and ethical feasibility of having robots move through crowded areas. These robots could be humanoids, service robots or assistive robots. “You hear a lot about self-driving cars, but not about robots that could be moving around among pedestrians,” says Aude Billard, the head of LASA. “However, robotics technology is clearly going in that direction, so we have to start thinking now about all that will imply.”

Many potential outcomes

The safety of robot users and those around them is the most evident issue among the many being researched. The lack of legislation that addresses this was discovered by LASA researchers, who then started to examine all the potential risks, including the possibility of colliding with a person.

For their risk analysis, the researchers used a robot they named Qolo, which stands for Quality of Life with Locomotion. Qolo is a standing wheelchair for individuals with disabilities that was first created at the University of Tsukuba in Japan. The wearer can effortlessly transition from a seated to a standing posture thanks to the device’s two powered wheels and passive exoskeleton.

In Bern, the LASA team tested the Qolo’s crashworthiness. Diego Paez, a postdoc at LASA, explains that “we conducted the tests with two types of dummies, as the effect of a collision can differ depending on how tall the person is.” For instance, the head is most vulnerable in youngsters, but the belly is most sensitive in pregnant women. The researchers found that even at low robot speeds, like < 6 km/h, collisions can result in severe injuries. Hence, avoiding these collisions is even more crucial.

The use of active navigation

Modifying Qolo to enable environment analysis and response was the first stage. The robot was outfitted by the scientists with a variety of sensors, including front-facing cameras and a Lidar system with lasers. “The robot must be able to see everything around it in 360 degrees in order to avoid obstructions in front of and behind it. Also, it needs to be aware of what is behind it in case it wants to fast reverse to avoid a collision “Paez says. “The cameras tell the robot whether the obstructions are pedestrians, and the Lidar system detects all kinds of impediments.”

Also, the team added bumpers on Qolo’s front. According to Paez, the bumpers alert the robot when it makes touch with something and quantify the force at which it makes contact, allowing the maximum force to be kept to a minimum while the robot is still in motion. In other words, Qolo is designed to avoid obstacles rather than stopping if it encounters one. For humans nearby the robot, a sudden stop in the middle of a crowd “may be even more deadly,” the expert warns.

To determine how many people are nearby and what directions they are travelling in, Qolo’s sensors data is merged with people detection and tracking algorithms. In order for Qolo to react fast in crowded areas, LASA researchers created a sophisticated navigation algorithm that enables it to determine the optimum course to take in only a few milliseconds.

predicting the unforeseen

Despite the inventors’ technological prowess, their robot is unable (yet) to anticipate abrupt actions such quick direction changes. “Since everyone responds to situations differently, it is difficult to predict what people will behave in various circumstances. We must therefore evaluate Qolo in practical settings “Paez explains. Thus the testing in the open market of Lausanne.

There, the engineers may gather important feedback on the user experience as well as all of the robot’s systems, including its hardware and algorithms. The early results are encouraging; it is very helpful for data collecting that pedestrians appear to act normally around the device. According to Paez, “We still need to examine the data, but it looks that the robot’s semi-autonomous dimension works effectively. Billard furthers: “By shifting their torsos, users instruct Qolo in which direction to go. The robot will react quickly to avoid an obstruction if it suddenly appears. For people with disabilities, that kind of guided navigation can be really helpful.”

Risk consciousness

With advancements in robotics taking place at a rapid pace, we could start seeing more and more such devices on our roads and sidewalks—like delivery robots, for example. The LASA team nevertheless stresses one crucial point: it will be essential to develop effective ways for minimizing the probability of collisions and other accidents. “Crash tests have shown that the risk of injury could be high and sometimes exceeds what’s permissible for automobiles,” says Paez.

“Now we need to work on a control system for mitigating this risk, whether by lowering the robot’s speed or improving its shock absorption capacity,” says Billard. “And it’s crucial for these findings to be taken into account in future legislation. These laws could include setting a speed limit for assistive robots like Qolo or restricting the ability of some kinds of vehicles, like delivery robots, to operate in highly frequented areas.”