In a groundbreaking development, engineers at the Massachusetts Institute of Technology (MIT) have created a new type of robotic gripper that uses reflexes to improve its grasp. This innovative development has the potential to revolutionize the field of robotics and bring about significant changes in industries like electronics and computers, where precision and speed are of utmost importance.
In the world of robotics, a common challenge is the “pick-and-place” operation. Here, robots are required to identify an object, pick it up, and place it in a different location. This process often involves complex programming languages and coding, and if the robot fails in its first attempt, it usually has to start all over again.
MIT’s novel design aims to change this by incorporating reflexes into the robotic planning architecture. The new gripper, unlike its predecessors, doesn’t start from scratch after a failed attempt. Instead, it adapts in real-time to roll, palm, or pinch an object for a better grip. These “last centimeter” adjustments are carried out without the need for a higher-level planner, much like how humans instinctively adjust their grip when they fumble for an object.
This is a significant leap forward in the field of robotics, as it is the first design to integrate reflexes into a robotic system. For now, this system is a proof of concept that provides a general organizational structure for embedding reflexes into a robotic system. However, the researchers are planning to program more complex reflexes to create more adaptable and nimble machines that can work with humans in ever-changing environments.
The current generation of robotic grippers are designed for slow and precise tasks such as assembling parts on a factory line. These systems rely heavily on visual data from onboard cameras to perform their tasks, which limits their reaction time, especially if they need to recover from a failed grasp.
The MIT team’s new work has overcome this limitation by building a more responsive platform that uses fast, responsive actuators originally developed for their mini cheetah robot. This new design includes a high-speed arm and two lightweight, multijointed fingers. It also incorporates custom high-bandwidth sensors at the fingertips that record the force and location of any contact, as well as the proximity of the finger to surrounding objects more than 200 times per second.
The robotic system is designed such that a high-level planner initially processes visual data of a scene, marking an object’s current location where the gripper should pick the object up, and the location where the robot should place it down. Then, the planner sets a path for the arm to reach out and grasp the object. At this point, the reflexive controller takes over. If the gripper fails to grab hold of the object, it quickly acts out any of three grasp maneuvers or “reflexes” in response to real-time measurements at the fingertips.
The engineers are now working on incorporating more complex reflexes and grasp maneuvers into the system. Their ultimate goal is to build a general pick-and-place robot capable of adapting to cluttered and constantly changing spaces. This development could have far-reaching implications for industries like electronics and computers that require high precision and speed in their operations.
For more information on this groundbreaking development, you can contact Abby Abazorius at This email address is being protected from spambots. You need JavaScript enabled to view it.; 617-253-2709.
