Recently, researchers at MIT described a system of software sensors that can cover a robot's body to provide "proprioception", that is, to sense the movement and position of its body. The feedback will enter a novel deep learning model, which can filter out noise and capture clear signals to calculate the 3D position of the robot.
MIT
Mechanical arm system with soft sensor, data diagram
It is understood that this soft robot arm can automatically swing and stretch, and predict its own space position. The soft sensor developed by the researchers is to cut the conductive silicon film into origami shape, so that they have "piezoresistance" characteristics, which means that they will change the resistance when they strain. When the sensor deforms in response to the tension and compression of the manipulator, its resistance is converted into an output voltage, which is then used as a signal related to the motion. The sensor can be made of human ready-made materials, which means that any laboratory can develop its own system in the future.
A fully integrated human body sensor is the long-term goal of soft robot technology. Traditional rigid sensors will damage the natural flexibility of soft robot, complicate its design and manufacture, and may lead to various mechanical failures. Therefore, sensor based on soft material is a more suitable alternative, but its design needs special material and program operation method, which makes it difficult for many robot laboratories to manufacture and integrate them in soft robot.
Dynamic drawing of mechanical arm
"We are sensing the soft robot's characteristics so that it can get feedback from sensors (rather than the visual system) for control, rather than through the visual system as before," the researchers said. For example, we want to use these soft robot trunks to automatically orient and control ourselves, pick up things and interact with the world. This is the first step towards this more complex automation. "
In the future, one of the goals of researchers is to help create artificial limbs that can handle and manipulate objects in the environment more nimbly.
Next, the researchers aim to explore new sensor designs to improve sensitivity and develop new models and deep learning methods to reduce the training time and process required for each new soft robot. They also hope to improve the system to better capture the complete dynamic motion of the robot. At present, the neural network and sensor skin of the soft robot are not sensitive to capture micro motion or dynamic motion. However, for the current learning based soft robot control method, this is an important first step.
One