Adopting Physical Artificial Intelligence in Soft Aerial Robots

Abstract

In recent years, there has been a lot more attention towards the utilization of physically intelligent features in robotics. In this work, we provide a perspective on the physical artificial intelligence (PAI) paradigm and its impact on the conceptualization, design, and manufacturing of current and future aerial robots and infrastructure. We highlight the theory, enabling technologies, system features, and the tasks that the PAI paradigm will improve beyond the current approaches with conventional rigid aerial robots. We also discuss the multi-disciplinary effort required to collaborate with and educate researchers in the development of physically intelligent robots. PAI promises to lead the development of a new era of robust flying robotic organisms that are capable of adapting to and performing multi-functional tasks autonomously in a complex and unstructured environment. Aerial robotics is a great field of study to validate PAI as a development methodology.

Design of CLARI: A Miniature Modular Origami Passive Shape‐Morphing Robot

“…CLARI is currently unable to move effectively without careful body-compliance tuning. This is not surprising because the role of body mechanics during legged locomotion as a morphological computation principle [45,48] is an area of active interest to Table 2. Comparing the shape morphing and complex terrain locomotion abilities of some of the successful legged platforms across sizes from a few millimeters to meters.…”

“…CLARI is currently unable to move effectively without careful body‐compliance tuning. This is not surprising because the role of body mechanics during legged locomotion as a morphological computation principle [ 45,48 ] is an area of active interest to biologists, [ 68,69 ] physicists, [ 70,71 ] and roboticists [ 72–74 ] alike and remains a challenging problem yet to be fully understood. [ 35,48 ] For example, the first couple of generations of the MIT Cheetah [ 75 ] featured a compliant backbone which was later abandoned [ 76 ] in part due to the challenges associated with tuning for effective locomotion.…”

“…[ 11 ] Our choice of articulated morphology for the robot body enables us to combine the rapid, autonomous, and multi‐gait locomotion capabilities of articulated laminate robots with the passive compliance‐based embodied physical intelligence of soft material systems. [ 45–48 ] Furthermore, we choose origami‐based design, [ 49 ] laminate fabrication, [ 50 ] and the pop‐up assembly process [ 51 ] for CLARI as it offers an easy methodology of tuning geometry‐based compliance (by varying flexure geometry) in addition to varying material properties (by changing individual layers) as needed within the laminate composite stacks of these robots at a variety of scales. [ 14 ]…”

Metamorphic aerial robot capable of mid-air shape morphing for rapid perching

“…Aerial robotic platforms can modify their structure during flight to go through different sized apertures 49 , 50 , protect themselves from collisions 51 , 52 , or grasp objects 53 , 54 . This idea can be extended further by using adaptable and programmable structures that can be formed from origami folding or soft materials 55 – 66 .…”

Koopman Operators for Modeling and Control of Soft Robotics

“…In contrast to their rigid counterparts, soft robots have bodies made out of intrinsically soft/or extensible materials, which exhibit unprecedented adaptation to complex environments and can absorb impact energy for safe interactions with the environment, other robots, and even humans [1]. Soft robots have been applied in all aspects of robotic research, including but not limited to assistive robotics [2]- [4], grasping [5]- [7], ground mobility [8], [9], legged locomotion [10], [11], aerial robots [12] and underwater robots [13].…”