What can robotics research learn from computer vision research?
This analysis could help robotics researchers adopt more effective methodologies to accelerate progress, though it is incremental as it builds on existing comparisons between fields.
The paper argues that robotics research progress is slower than computer vision due to differences in research methodology, such as evaluation under strict constraints and bold numbers versus experiments and videos.
The computer vision and robotics research communities are each strong. However progress in computer vision has become turbo-charged in recent years due to big data, GPU computing, novel learning algorithms and a very effective research methodology. By comparison, progress in robotics seems slower. It is true that robotics came later to exploring the potential of learning -- the advantages over the well-established body of knowledge in dynamics, kinematics, planning and control is still being debated, although reinforcement learning seems to offer real potential. However, the rapid development of computer vision compared to robotics cannot be only attributed to the former's adoption of deep learning. In this paper, we argue that the gains in computer vision are due to research methodology -- evaluation under strict constraints versus experiments; bold numbers versus videos.