Overview
The upcoming workshop titled “Learning Representations for Planning and Control” is set to occur at the IROS conference in Macau on November 8, 2019. This event aims to bridge the gap between traditional planning and control algorithms and recent advancements in machine learning, fostering collaboration and innovation in these intersecting fields.
Background & Relevance
The integration of machine learning techniques into planning and control systems has become increasingly important. Traditional methods face challenges such as computational efficiency and the curse of dimensionality. Recent advancements in machine learning provide new avenues for overcoming these obstacles, enabling systems to make complex decisions based on raw sensory data. This workshop will serve as a platform for researchers to discuss and explore these developments, enhancing the theoretical foundations and practical applications of planning methods.
Key Details
- Workshop Date: November 8, 2019
- Location: IROS, Macau
- Submission Deadlines:
- Extended Abstract Submission: August 20, 2019, 6 PM PST
- Acceptance Notification: September 20, 2019, 6 PM PST
- Camera-Ready Submission: October 5, 2019, 6 PM PST
- Submission Link: CMT Submission
Eligibility & Participation
The workshop invites contributions from researchers and practitioners in the fields of planning and control, particularly those who are exploring the intersection with machine learning. It is suitable for individuals looking to share their insights and advancements in these areas.
Submission or Application Guidelines
Participants are encouraged to submit extended abstracts (2-3 pages, excluding references) that may include original research, late-breaking results, or literature reviews relevant to the workshop’s themes. Accepted papers will require a camera-ready submission of 3-6 pages. All submissions must adhere to the IEEE Conference Templates for formatting.
Additional Context / Real-World Relevance
The workshop addresses significant challenges in planning and control, such as data efficiency and the need for formal guarantees in machine learning-based methods. By bringing together experts from both fields, the event aims to foster innovative solutions that can be applied in real-world scenarios, enhancing the capabilities of autonomous systems and robotics.
Conclusion
This workshop presents an excellent opportunity for researchers to engage with peers, share their work, and contribute to the evolving landscape of planning and control in the context of machine learning. Interested participants are encouraged to submit their work and participate in discussions that could shape future research directions in this critical area.
Category: Conferences & Workshops
Tags: planning, control, machine learning, data-driven approaches, imitation learning, representation learning, IROS, IEEE, adaptive sampling, collision detection
