Swarm of tiny drones explores unknown environments
This work, presented in Science Robotics on 23 October, forms a significant step in the field of swarm robotics. The challenge comes from the fact that the tiny 33-gram drones need to navigate autonomously while having extremely limited sensing and computational capabilities. The joint research team – with researchers from TU Delft, University of Liverpool and Radboud University of Nijmegen – tackled this challenge by drawing inspiration from the relative simplicity of insect navigation.
Inspiration from nature
Insect swarms have inspired roboticists to think that small robots may also be able to overcome their individual limitations by operating in a swarm. Swarms of small and cheap robots would be able to perform tasks that are currently out of reach of large, individual robots. For instance, a swarm of small flying drones would be able to explore a disaster site much quicker than a single larger drone. Such swarms have not been realised yet.
Over the last four years, a joint research team of the universities of TU Delft, University of Liverpool, and Radboud University of Nijmegen, financed by the Dutch national science foundation NWO Natural Artificial Intelligence programme, has strived to design a swarm of tiny drones able to explore unknown environments. The goal of the research project was to make steps towards using swarms of drones in search-and-rescue scenarios.
The main idea was that in the future, rescue workers will be able to release a swarm of tiny drones to explore a disaster site such as a building that is about to collapse. The swarm of drones will enter the building, explore it, and come back to the base station with relevant information. The rescue workers can then focus their efforts on the most relevant areas – for instance, where there are still people inside.
In the project tiny drones were equipped with cameras and sent out in an indoor office environment to find two dummies representing victims in a disaster scenario. This proof-of-concept search-and-rescue task clearly showed the advantage of having a swarm. Within 6 minutes, a swarm of 6 drones was able to explore about 80% of the open rooms – which would be impossible for one of the drones alone. Furthermore, swarming also turned out be useful for redundancy. One drone found a victim, but due to a hardware failure of the camera, it could not bring back any images. Luckily, another drone captured the victim on camera as well.
“The biggest challenge in achieving swarm exploration lies at the level of the individual intelligence of the drones”, says Kimberly McGuire, the PhD student who has performed the project. “In the beginning of the project, we focused on achieving basic flight capabilities such as controlling the velocity and avoiding obstacles. After that, we designed a method for the small drones to detect and avoid each other. We solved this by having each drone carry a wireless communication chip and then making use of the signal strength between these chips – this is like the number of bars shown on your phone that decrease when you move away from your WiFi router in your home. The main advantages of this method are that it does not require extra hardware on the drone and that it requires very few computations.”
The most daunting challenge in the way of swarm exploration, is the difficulty of making small robots navigate an unknown environment by themselves. The reason for this is that tiny robots are very limited in terms of sensing and computation.
Again, nature provided important inspiration. Insects do not make highly detailed maps. Instead, they retain landmarks and behaviorally relevant places like food sources and their nest. “The main idea underlying the new navigation method is to reduce our navigation expectations to the extreme: we only require the robots to be able to navigate back to the base station”, says Guido de Croon, principal investigator of the project. “The swarm of robots first spreads out into the environment by having each robot follow a different preferred direction. After exploring, the robots return to a wireless beacon located at the base station.”
“The proposed navigation method is a novel type of bug algorithm”, adds Kimberly McGuire. “Bug algorithms do not make maps of the environment but deal with obstacles on the fly. In principle, detailed maps are very convenient, because they allow a robot to navigate from any point in the map to any other point, along an optimal path. However, the costs of making such a map on tiny robots is prohibitive. The proposed bug algorithm leads to less efficient paths but has the merit that it can even be implemented on tiny robots.”
The Latest on: Swarm robotics
via Google News
The Latest on: Swarm robotics
- First "AI War": Israel Used World's First AI-Guided Swarm Of Combat Drones In Gaza Attackson July 2, 2021 at 4:26 am
In the ongoing conflict between Israel and the Occupied Palestinian Territory, the Israel Defense Forces (IDF) has deployed AI and supercomputers to identi ...
- Neural network to study crowd physics for training urban robotson June 30, 2021 at 6:10 am
The chaotically moving objects dense clusters digital twin is being developed by students from NUST MISIS, ITMO and MIPT to navigate robots. It is going to be a web service using graph neural networks ...
- Floating Fire Ant Rafts Form Mesmerizing Amoeba-Like Shapeson June 29, 2021 at 4:01 pm
Researchers say the morphing colonies help ants feel for solid land in a flooded environment—and might inspire swarming robots one day ...
- Servos And Services—How An Outdoor Advertising Company Became A Player In U.K. Roboticson June 29, 2021 at 1:14 pm
But the real change in robotics is in the service proposition. We are helping companies develop new services and levels of service.” He cites the example of Ocado. The company uses a swarm of ...
- Enzyme-powered nanorobots behave like a swarmon June 29, 2021 at 2:08 am
Enzyme-powered nano-sized robots hold exciting possibilities for biomedicine because they could navigate around the body autonomously to target tumors or specific organs. Now researchers show that it ...
- Grene Robotics develops indigenous drone defence domeon June 28, 2021 at 6:05 am
The autonomous defence weapon system uses Artificial Intelligence, cybersecurity and robotics to identify and counter threats ...
- Global Swarm Robotics Market 2021 Status and Outlook, Future Estimations with Top Key Players, Application and Segmentation by 2026on June 26, 2021 at 2:19 am
The latest updated exclusive report published by MRInsightsbiz entitled Global Swarm Robotics Market Growth 2021-2026 provides a cumulative overv ...
- Simulations, real robots, and bloopers from the DOTS competition: Powering emergency food distribution using swarmson June 24, 2021 at 7:20 am
Simulations, real robots, and bloopers from the DOTS competition: Powering emergency food distribution using swarms ...
- This Robot Swarm Gets Smarter The More It Workson June 19, 2021 at 8:31 am
Advertisement Are you ready for autonomous robots that learn the more they work? I sure am not. This might be the beginning of the end. The start of SkyNet. A robotics company called Geek+ just said ...
via Bing News