Four-legged SPOT from Boston Dynamics arrives at FEE CTU to increase our chances in the finals of DARPA SubT Challenge.
It can overcome obstacles the fastest even in difficult terrain, it can safely climb stairs and it can wade through mud and water. The four-legged autonomous SPOT robot from Boston Dynamics joined our team to increase our chances in the finals of the prestigious DARPA Subterranean (SubT) Challenge, which takes place on September 21-23, 2021 in Kentucky, USA. Apart from participating in the competition, SPOT will be used in additional research in the field of autonomous movement in human-inhabited environments.
Our team of about 20 researchers competing under the flag of CTU-CRAS-NORLAB (Czech Technical University - Center for Robotics and Autonomous Systems - Northern Robotics Laboratory) will set out for the underground complex MegaCavern in Kentucky to defend the third place from the previous two rounds. As the best unsponsored team, we managed to make a name for ourselves in the international competition of representatives from prestigious research institutions (including NASA, MIT, CMU, OSU, CalTech, Oxford and ETH Zurich). In December 2020, CTU-CRAS-NORLAB was funded with a 1,5 million USD (32,6 million CZK) grant from the US Department of Defense Advanced Research Projects Agency (DARPA) which put the team in the category of sponsored competitors.
"This subsidy allowed us to invest in the purchase of state-of-the-art robotic hardware. Now, we can fully compare ourselves to the best in terms of technological equipment," says Tomáš Svoboda, head of the Department of Cybernetics at FEE CTU and head of the CTU-CRAS-NORLAB team. According to Tomáš, the biggest challenge will be their rapid integration with the team of existing robots so that they can effectively exchange information in an environment without GPS signal. "The conditions of caves do not allow the robots to be controlled manually by the operator and are therefore dependent exclusively on their autonomous movement, decision-making and mutual coordination during the competition. These are the autonomous skills of planning and cooperation of robots in the performance of research and search tasks that will decide which of the eight finalists in MegaCavern succeed," he explains.
The DARPA Subterranean (SubT) Challenge simulates a real-life rescue situation after a landslide or disaster. The task for the robotics teams is to identify as many objects as possible, such as people, telephones or backpacks, or detect escaping gas in an unknown environment in one hour. The final round is not only about the total reward of 3,5 million USD for the first three teams, but also prestige. The findings of scientists will then find application in time-critical defense or civilian operations such as "search and rescue".
How to transform SPOT into a member of the rescue team in four months
The heterogeneity of the hardware equipment of our team places demands especially on the integration of their software. “Each of our wheeled, crawler, flying and six-legged rescue robots, with which we completed the previous rounds of the DARPA SubT Challenge, is somehow different, has a specific way of moving and consists of dozens of subsystems. A four-legged SPOT has now been added, which is perfectly suitable for autonomous movement in difficult terrain, mainly thanks to the unique walking algorithms developed by Boston Dynamics," says Jan Faigl, head of the robotics research in AIC.
"Our immediate task will be to create another layer over the native SPOT software that will match the conditions of the competition and ensure that our SPOTs can orient themselves in an unfamiliar environment. The goal is for our robots to be able to communicate with each other in the underground complex and to perform the tasks of rescuers in a coordinated manner,” he adds.
In order for SPOT to become a full member of the DARPA Subterranean (SubT) Challenge final set, there are several things the researchers need to take care of. SPOT’s four built-in cameras need to be supplemented with a LIDAR terrain mapping sensor, cameras with better optical properties and other computing devices running on neural networks that are capable of identifying objects and locating the robot in a dynamically generated 3D environment map. Computers will plan and evaluate the robot's trajectory to avoid obstacles. With regard to its load and consumption, it will be necessary to expand the battery to keep it in operation during the sixty-minute competition round.
An integral part of such a complex project is testing. The typical way of testing each individual part using a simulator is not suitable in this case, because the simulator is not able to simulate extreme environments where fog, mud, dust, or absence of GPS signal may occur. Therefore it is tested in real life, first in the lab at the university, then in suitable terrain.
Further research possibilities open up after the final round in Kentucky
The work of the FEE CTU robotics team is far from over with the final round. The most valuable part of the competition is the experience gained from a demanding environment where robots have the task of replacing humans. "We are already looking for possibilities of follow-up research. One of the topics is related to building a relatively cheap communication infrastructure that will help in rescue missions and solve challenges in environments such as caves or underground, where it is difficult to spread the signal," says Jan Faigl.
Another big topic is the localization of autonomously controlled robots. In the case of autonomous robot movement, for example in Prague, much more accurate localization will be needed than current technologies offer. Research in this area is underway and SPOT, as the best current platform for movement in an environment that is intended for humans, gives us the opportunity to get involved.
"In an environment used by people, such as offices, production facilities or streets, it is important that the robot moves correctly and empathetically. So far, the robot attracts the attention of people and they avoid it, but if, for example, SPOT is deployed in everyday use, it is expected that it does not interfere and is able to coexist with humans," explains the application scenario of further research Jan Faigl. The last direction of research of walking robots are walking methods, which are a great challenge for academics in terms of movement stability in a demanding environment and its effectiveness.