What would enable to faster progress in robotics research?
Part 2: Historians
One of the other things that would help us progress faster is a better understanding of what ideas have already been tried.
Trite, I know, and readily apparent, and something that applies across most (all?) scientific domains. We’re not an established field like Biology or Chemistry, and we’re effectively still at the very beginning of defining the laws and principles that will be our foundations. If we don’t know what approaches have been tried and failed, and have some sense of why, we won’t be able to define those laws and principles.
There are many researchers without a good sense of the different branches of robotics. Because we need breadth across disciplines simply to function in robotics, it is easy to lose sight of the fact that we actually need more breadth, rather than less.
Each researcher is focusing on a small part of the whole. On graph based planning tools, or case based reasoning, or SLAM, or the vacation snapshot problem.
Each researcher’s small part is in a small part of the overall robotics ecosystem. In the world of path planning algorithms, or the world of long endurance underwater robots, or the world of air robots for agriculture, or the world of industrial robot arms or the world of androids designed to look exactly like humans.
And each of those small parts is in turn a small part of the larger robotics research effort underway around the globe. Just within the aerial robotics community there are separate subgroups that communicate with each other very little. The fixed wing agricultural robotics community has little to say to the researchers working on indoor operations with small quadcopters. The groups contributing to the automation of commercial and military fixed wing aircraft often don’t interact with the medium size rotary wing community.
We have breadth across the disciplines of electrical engineering, mechanical engineering, and computer science, and we recognize that every robot is the result of a group of people each contributing components from their own expertise. But we often fail to recognize that the field of robotics itself is even broader and more disparate than the disciplines that contribute to it.
And beyond this breadth of current research, there is the depth of historical perspective.
The problem is that the history of a given tendril of robotics may be well understood by its practitioners, but as these vines thicken and mature, they begin to run into problems that were addressed and solved (or at least partially solved) in other tendrils.
For example, the industrial robotics research community broke off from the research community in the 1970s, with the first push to automate factories. In the late 1980s, the research community split as one set of more theoretically-minded researchers focused on developing artificial intelligence and the other, more concerned with practical implementations, focused on developing systems that would work in the physical world, while the industrial robotics community still saw themselves as the core of the robotics community. In the intervening thirty years, the industrial robotics community has achieved significant development and penetration into industrial operations, but has largely failed to recognize the huge strides made in the less rigorous autonomous mobile robotics community, and the similarly huge strides made in the more rigorous artificial intelligence-based robotics community. Often, instead of taking advantage of this progress, they are instead rediscovering algorithms originally developed in the late 1980s in the reactive robotics community. Very few researchers know the history of work done outside their own specialties, and their own systems suffer as a result.
Better awareness of the history of robotics as a whole would prevent researchers from duplicating approaches and algorithms without realizing it and allow us to benefit from all the work done in the past. We need courses, or textbooks, or webisodes – something that will allow newcomers and the experienced alike to learn the history of work that might apply. We need historians to curate that information and make it available, to analyze it and understand how the pieces fall together, in order to define the principles behind the robots that work.