[2001.02366] What can robotics research learn from computer vision research?contact arXivarXiv Twitter

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.

2 mentions: @iandanforth@_yayan24
Date: 2020/01/20 20:20

Referring Tweets

@iandanforth Inspired by the latest ImportAI (@jackclarkSF) and t.co/xXTedFmUEC (@RoboticVisionAU) I'd like to take a moment to talk about Waldoing. Waldoing is the remote operation of a robotic manipulator by a human. 1/n

Related Entries

Read more Speech-to-speech translation
0 users, 3 mentions 2019/04/15 23:16
Read more Adaptation Data Selection using Neural Language Models: Experiments in Machine Translation - ACL Ant...
0 users, 1 mentions 2019/10/01 14:18
Read more Reading: An Effective Approach to Unsupervised Machine Translation (Artetxe et al. ACL 2019) - Speak...
0 users, 1 mentions 2019/12/07 05:20
Read more Bleu: a Method for Automatic Evaluation of Machine Translation - ACL Anthology
0 users, 1 mentions 2020/06/06 05:21
Read more US20200104371A1 - Systems and methods for simultaneous translation with integrated anticipation and ...
0 users, 1 mentions 2020/07/03 06:53