Described as a “step toward automation of robot design”, the algorithm was developed by researchers at the Massachusetts Institute of Technology (MIT).
For robots to reliably complete their programmed duties, they need to know the whereabouts of all their body parts – but, the researchers said, “that's a tall task for a soft robot that can deform in a virtually infinite number of ways”.
The deep-learning algorithm suggests an optimised placement of sensors within the robot's body, allowing it to better interact with its environment and complete assigned tasks.
“The system not only learns a given task, but also how to best design the robot to solve that task,” said co-lead author Alexander Amini. “Sensor placement is a very difficult problem to solve, so having this solution is extremely exciting.”
The co-lead authors were Amini and Andrew Spielberg, both PhD students in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). Other co-authors include MIT PhD student Lillian Chin, and professors Wojciech Matusik and Daniela Rus.
Rigid robots' finite array of joints and limbs usually makes for manageable calculations by the algorithms that control mapping and motion planning. Flexible and pliant soft robots are not so easy to deal with, however.
“The main problem with soft robots is that they are infinitely dimensional,” said Spielberg. “Any point on a soft-bodied robot can, in theory, deform in any way possible.”
That makes it difficult to design a soft robot that can map the location of its body parts. Past efforts have used an external camera, but the researchers wanted to create a soft robot untethered from external aid.
“You can't put an infinite number of sensors on the robot itself,” said Spielberg. “So, the question is ‘How many sensors do you have, and where do you put those sensors in order to get the most bang for your buck?’"
The researchers developed a novel neural network architecture that optimises sensor placement and learns to efficiently complete tasks. First, the researchers divided the robot's body into regions called particles. Each particle's rate of strain was provided as an input to the neural network. Through a process of trial and error, the network learns the most efficient sequence of movements to complete tasks, like gripping objects of different sizes. At the same time, the network keeps track of which particles are used most often, and it removes the lesser-used particles from the set of inputs for the network's subsequent trials.
By optimising the most important particles, the network also suggests where sensors should be placed on the robot to ensure efficient performance. In a simulated robot with a grasping hand, for example, the algorithm might suggest that sensors be concentrated in and around the fingers, where precisely-controlled interactions with the environment are vital for manipulating objects. While that may seem obvious, the algorithm ‘vastly outperformed’ humans' intuition on where to put the sensors.
The team pitted their algorithm against a series of expert predictions. For three different soft robot layouts, the team asked roboticists to manually select where sensors should be placed to enable the efficient completion of tasks like grasping various objects. Then they ran simulations comparing the ‘human-sensorised’ robots to the ‘algorithm-sensorised’ robots.
“Our model vastly outperformed humans for each task, even though I looked at some of the robot bodies and felt very confident on where the sensors should go,” said Amini. “It turns out there are a lot more subtleties in this problem than we initially expected.”
Spielberg said the work could help to automate robot design. In addition to developing algorithms to control a robot's movements, “we also need to think about how we're going to sensorise these robots, and how that will interplay with other components of that system,” he said.
Better sensor placement could have industrial applications, especially where robots are used for fine tasks like gripping. “That's something where you need a very robust, well-optimised sense of touch,” said Spielberg. “So there's potential for immediate impact.”
Co-author Rus said: “Automating the design of sensorised soft robots is an important step toward rapidly creating intelligent tools that help people with physical tasks. The sensors are an important aspect of the process, as they enable the soft robot to ‘see’ and understand the world and its relationship with the world.”
The research will be presented during April's
IEEE International Conference on Soft Robotics and published in the journal
IEEE Robotics and Automation Letters.
Want the best engineering stories delivered straight to your inbox? The Professional Engineering newsletter gives you vital updates on the most cutting-edge engineering and exciting new job opportunities. To sign up, click here.
Content published by Professional Engineering does not necessarily represent the views of the Institution of Mechanical Engineers.