This Modular Robot Can Perform Complex Tasks by Augmenting Its Environment Autonomously

Robots are primarily created to aid us in performing many complex tasks that we otherwise fail to do or take a considerable amount of time in completing. However, most robots that we see today are designed to perform specific tasks, and most of them do not have the capability to adapt to the natural, unstructured environment.

Such robots may perform well inside a robotics lab, but fail to understand and adapt to day-to-day situations. But, designing a robot that can do more things than one and adapt to changes is a mammoth task and requires a lot of engineering and creative thought process.

However, researchers at the University of Pennsylvania have achieved a remarkable success in this direction. Their robot is inspired by the human tendency to modify the surrounding environment to handle a different kind of situation.

In many cases, we humans make use of objects around our environment to complete different tasks. For example, making use of stairs and ramps to reach high places, or attaching handles to the objects to move them easily.

This is precisely what the University of Pennsylvania’s Modlab did. Instead of creating a single robot that can do a specific set of operations, they made a series of self-assembling modules that can combine themselves to undertake a wide variety of tasks.

The SMORES-EP (Self-Assembling Modular Robot for Extreme Shapeshifting – Electro Permanent magnets) is a robot made from a set of wheeled cubes, which can attach to each other magnetically. The robot was recently presented at the IEEE International Conference on Robotics and Automation.

The perk of designing modules that magnetically attach to each other gives SMORES-EP the ability to form many different configurations, allowing it do multiple things that otherwise a normal robot can’t.

This robot also has the ability to modify its environment to suit the need to complete the objective. The robust imaging system integrated within the robot uses an RGB camera that allows it to see and gauge objects, distances, heights, gaps, etc.

The video shows the ability of SMORES-EP to solve the problem on how to scale heights and cross gaps or short distances.

The system is assigned a specific task to complete. Few objects are placed in the environment for it to use in case if it needs, but without any explicit instructions on what to do every time.

[see-also]

Depending on the situation, the robot modules autonomously decide on making use of surrounding objects to accomplish the task. In cases where the task seems impossible to complete, even with the assisting objects, the system disassembles itself.

While ramp and blocks are just an example of objects that can be used by the robot to modify the environment, the possibilities are endless with such a system. There are many different ideas that can be considered and we are only scratching the surface on the capabilities of autonomous robots.