I’ve never really been a fan of baseball. Maybe I don’t fully grasp the nuances of the game. Maybe I don’t appreciate the talent and strategy of the teams. Maybe my short attention span is to blame. (Thank you, TikTok.) Truthfully, I’ve attended more concerts at baseball stadiums than I have actual baseball games. So, what could make this sport more appealing, especially for younger generations? A team made up entirely of drones, of course. While it might seem impossible for a drone to be able to catch and throw a baseball, researchers have developed an innovative drone that can grasp and move objects at impressive speeds. 

Researchers at the Massachusetts Institute of Technology’s (MIT’s) SPARK Lab have created a drone that can quickly grab and move objects. The team combined a soft aerial manipulator with a fully onboard perception pipeline that is capable of aggressive grasping. According to the team, the soft gripper is essential in mitigating the effect of positioning errors from the perception pipeline and reduces reaction forces faced at high speeds or from environmental contact. The soft gripper is comprised of four foam fingers and attached to a quadrotor frame.

To ensure their system was working properly, the team conducted 180 flight tests. The team was able to demonstrate grasps at up to 2 m/s. Additionally, the drone can be used in both indoor and outdoor environments without any external localization infrastructure. The drone can even grasp moving targets thanks to motion capture. 

The research team recently published their finding in a paper titled “High-speed aerial grasping using a soft drone with onboard perception.” In an excerpt from the research paper, the team writes, “Contrary to the stunning feats observed in birds of prey, aerial manipulation and grasping with flying robots still lack versatility and agility. Conventional approaches using rigid manipulators require precise positioning and are subject to large reaction forces at grasp, which limit performance at high speeds. The few reported examples of high-speed aerial grasping rely on motion capture systems, or fail to generalize across environments and grasp targets. We describe the first example of a soft aerial manipulator equipped with a fully onboard perception pipeline, capable of robustly localizing and grasping visually and morphologically varied objects. 

The proposed system features a novel passively closed tendon-actuated soft gripper that enables fast closure at grasp, while compensating for position errors, complying to the target-object morphology, and dampening reaction forces. The system includes an onboard perception pipeline that combines a neural-network-based semantic keypoint detector, a state-of-the-art robust 3D object pose estimator, and a fixed-lag smoother to estimate the pose of known objects. The resulting pose estimate is passed to a minimum-snap trajectory planner, tracked by an adaptive controller that fully compensates for the added mass of the grasped object. Finally, a finite-element-based controller determines optimal gripper configurations for grasping.”