This workshop will bring together renowned experts from both the computer vision and robotics communities to discuss crucial challenges arising when deploying deep learning methods in real-world robotic applications, and identify the necessary research directions to meet these challenges.
As a major concrete outcome and activity, the workshop will discuss a set of future large scale robotic vision benchmarks to address the critical challenges for robotic perception that are not yet covered by existing computer vision and robotics benchmarks, such as performance in open-set conditions, incremental learning with low-shot techniques, Bayesian optimisation, active learning, and active vision.
These new benchmarks will complement existing benchmark competitions and will be run as an annual challenge at CVPR and ICRA. They will help to close the gap between computer vision and robotics, and will foster crucial advancements in machine learning for robotic vision.
Our workshop will be on Friday 22 June 2018, in Room 150 - G.
Participate in the panel discussion and ask your questions for the panel discussion here.
A robot or autonomous system often operates in uncontrolled and detrimental conditions that pose severe challenges to its perception system. Robots are inherently active agents that act in, and interact with the physical real world. They have to make decisions based on incomplete and uncertain knowledge, with potentially catastrophic results.
Computer vision challenges and competitions like ILSVRC or COCO had a significant influence on the advancements in object recognition, object detection, semantic segmentation, image captioning, and visual question answering in recent years. These challenges posed motivating problems to the computer vision and machine learning research communities and proposed datasets and evaluation metrics that allowed to compare different approaches in a standardized way.
However, visual perception for robotics faces challenges that are not well covered or evaluated by the existing benchmarks. Some of those specific challenges for robotic vision and topics of interest for the workshop are:
With support by