Robots can be made from soft materials but the flexibility of such robots is limited by the inclusion of rigid sensors necessary for their control. Researchers have created embedded sensors that replace rigid sensors and offer the same functionality but with greater flexibility. Soft robots can be more adaptable and resilient than more traditional rigid designs. The team used machine learning techniques to create their design.
Automation is an increasingly important subject and central to this concept are the often paired fields of robotics and machine learning. The relationship between machine learning and robotics is not just limited to the behavioral control of robots but is also important for their design and core functions. A robot that operates in the real world needs to understand its environment and itself in order to navigate and perform tasks.
If the world was entirely predictable, a robot would be fine moving around without the need to learn anything new about its environment. But reality is unpredictable, so machine learning helps robots adapt to unfamiliar situations. Although this is theoretically true for all robots, it is especially important for soft-bodied robots as the physical properties of these are intrinsically less predictable than their rigid counterparts.
Take, for example, a robot with pneumatic artificial muscles (PAM) and rubber and fiber-based, fluid-driven systems that expand and contract to move. PAMs inherently suffer random mechanical noise and hysteresis, which is essentially material stress over time. Accurate laser-based monitors help maintain control through feedback but the rigid sensors restrict a robot’s movement.
The team sought to model a PAM in real time and maintain good control; however, given the ever-changing nature of PAMs, this is not realistic with traditional methods of mechanical modeling. So, the team turned to a powerful and established machine learning technique called reservoir computing in which information about a system — in this case, the PAM — is fed into a special artificial neural network in real time, so the model is ever changing and thus adapts to the environment.
The electrical resistance of PAM material changes, depending on its shape, during a contraction. The data is passed to the network so it can accurately report on the state of the PAM. Since ordinary rubber is an insulator, carbon was incorporated into the material to more easily read its varying resistance. The system emulated the existing laser-displacement sensor with equally high accuracy in a range of test conditions.
Thanks to this method, a new generation of soft robotic technology may be possible. This could include robots that work with humans — for example, wearable rehabilitation devices or biomedical robots — as the extra-soft touch means interactions with them are gentle and safe. Reservoir computing could be used in applications such as remote sensing that requires real-time information processed in a decentralized manner.
For more information, contact Kohei Nakajima at