Overview
The NeurIPS 2019 Workshop on Robot Learning invites researchers to submit papers addressing the challenges of applying machine learning techniques in real-world robotic systems. This workshop aims to explore the latest advancements in robot learning, particularly in the context of control and interaction in dynamic environments.
Background & Relevance
The field of robotics is rapidly evolving, with learning-based methods enhancing the capabilities of autonomous systems. However, deploying these methods in real-world scenarios remains a significant challenge due to various factors, including the need for extensive labeled data, safety concerns, and the complexity of real environments. Addressing these issues is crucial for the advancement of robotics and its integration into everyday life, where robots can assist humans in complex tasks.
Key Details
- Workshop Dates: 13th or 14th December 2019
- Location: Vancouver Convention Center, Vancouver, Canada
- Submission Deadline: 9th September 2019 (AOE)
- Acceptance Notification: 1st October 2019 (AOE)
- Camera-Ready Deadline: 1st December 2019 (AOE)
- Submission Link: CMT Submission
Eligibility & Participation
This workshop targets researchers and practitioners in the field of robotics and machine learning. Submissions are encouraged from those who have developed novel algorithms or conducted empirical evaluations on real robotic systems.
Submission or Application Guidelines
- Manuscripts should be a short research paper of up to 4 pages (excluding references) in LaTeX format.
- The main text must include all necessary figures and adequately describe the work, its contributions, and limitations.
- All submissions must be anonymized and submitted via the provided link by the deadline.
- Work that has appeared or is scheduled to appear in other venues must be significantly extended to be eligible for submission.
Additional Context / Real-World Relevance
The workshop will focus on key challenges in robot learning, including the need for robust algorithms that can operate safely in unpredictable environments. Topics such as transfer learning, safety, and simulation-to-real transfer are particularly relevant, as they address the gaps between theoretical research and practical applications. The insights gained from this workshop will contribute to the broader field of AI and its application in robotics, enhancing the capability of robots to assist in various tasks.
Conclusion
Researchers interested in the intersection of machine learning and robotics are encouraged to submit their work to this workshop. This is a valuable opportunity to engage with peers and contribute to the ongoing discourse on overcoming the challenges of real-world robot learning. Explore this opportunity and share your insights with the community.
Category: CFP & Deadlines
Tags: robotics, machine learning, neural networks, transfer learning, safety, real-world applications, domain adaptation, uncertainty quantification
