CROWDBOT: A crowd-aware shared-control wheelchair navigation system

Location: United Kingdom

Our smart wheelchair is built on a standard power wheelchair, with additional ultrasonic sensors, a laser scanner and a RGB-D camera. — Our smart wheelchair

Follow CROWDBOT on Twitter: @CrowdbotP

CROWDBOT (aka “Safe Robot Navigation in Dense Crowds”) is an EUR 4M Horizon 2020 consortium of five universities and two industrial partners:

INRIA, France (co-ordinator);
EPFL, Switzerland;
ETHZ, Switzerland;
RWTH, Germany;
UCL, UK;
SBR Europe, France; and
LOC GmbH, Germany.

CROWDBOT will enable mobile robots to navigate autonomously and assist humans in crowded areas, rather than simply stopping when the going gets tough.

The project will fill the gap in knowledge about close interactions between robots and humans during navigation tasks. In particular, CROWDBOT considers three realistic scenarios:

a semi-autonomous wheelchair that will adapt its trajectory to unexpected movements of people in its vicinity;
the commercially available Pepper robot that will navigate in dense crowds, whilst actively approaching people to assist them;
the cuyBot (under-development) that will adapt to compact crowds, as well as to being touched and pushed by people.

Dr Tom Carlson (PI, Aspire Create) and Dr Cathy Holloway will lead a core workpackage on the co-design and evaluation of the CROWDBOT system, as well as developing one of the demonstrators: a crowd-aware shared-control wheelchair. Bingqing (Pat) Zhang is a PhD student working on this project.

Shared-Control Navigation

We’ve all heard of autonomous systems (self-driving cars etc.), but in some cases fully autonomous systems aren’t really what the users want. For example, most wheelchair users do not want to be treated simply like precious pieces of cargo and ferried around automatically from point A to point B. Instead they want to be empowered to get around by themselves so they can continue with their activities of daily as independently as possible. However, there are some instances when environmental barriers such as narrow passageways, rough terrain and indeed crowds of oblivious pedestrians rather hamper their efforts. In cases such as these, we propose a “shared control navigation”, whereby the wheelchair itself is able to actively assist the user in safely and efficiently maneuvering through these difficult situations, without taking away their overall control authority. It is important to note that every individual is unique, so any such shared control system should be able to adapt to the needs and capabilities of that particular user.

For more information, check the project website: crowdbot.eu

Video: https://drive.google.com/file/d/1-xYeRGTvwB1repF1otKoIeuv8k0drfx6/view?usp=sharing