NeurIPS19 WS on Robot Learning: Control and Interaction in the Real World
NeurIPS Robot Learning 2019
- URL: http://www.robot-learning.ml/2019/
- Event Date: 2019-12-13 ~ 2019-12-14
- Submission Date: 2019-09-09
- Location: Vancouver, Canada
Call for Papers: NeurIPS19 WS on Robot Learning: Control and Interaction in the Real World
Vancouver Convention Center, Vancouver, Canada
13th or 14th December 2019
http://www.robot-learning.ml/2019/
The growing capabilities of learning-based methods in control and robotics have precipitated a shift in the design of software for autonomous systems. Recent successes fuel the hope that robots will increasingly perform varying tasks working alongside humans in complex, dynamic environments. However, the application of learning approaches to real-world robotic systems has been limited because real-world scenarios introduce challenges not arising in simulation. We focus on three broad challenges that currently preclude the deployment of machine learning methods on real systems:
Most current machine learning methods rely on large quantities of labeled data. While raw sensor data is available at high rates, the required variety is hard to obtain and the human effort to annotate or design reward functions is an even larger burden.
Algorithms must guarantee some measure of safety and robustness to be deployed in real systems that interact with property and people. Instantaneous reset mechanisms, as common in simulation to recover from even critical failures, present a great challenge to real robots.
The real world is significantly more complex and varied than curated datasets and simulations. Successful approaches must scale to this complexity, be able to adapt to novel situations and recover from mistakes.
We invite submissions that focus on tackling these challenges resulting from operation in the real world. We will encourage submissions that experiment on physical systems, and specifically consider algorithmic developments aimed at tackling the challenges presented by physical systems. A non-exhaustive list of relevant topics is:
transfer and multitask learning
explicit methods for planning
uncertainty quantification
safety and robustness
simulation-to-real transfer and domain adaptation
model learning
Deadlines
Submission Deadline: 9th September (AOE)
Acceptance Notification: 1st October (AOE)
Camera-Ready Deadline: 1st December (AOE)
Format
Manuscripts should be a short research paper of at most 4 pages long (excluding references) in the LaTeX format defined here. The main text should include all text and figures, and should adequately describe the work, its contributions, and its limitations. Manuscripts must be anonymized.
Please submit your extended abstract via https://cmt3.research.microsoft.com/NEURIPSWRL2019 by the deadline given above.
Contact neuripswrl2019@robot-learning.ml
Selection Criteria
All submissions will be peer reviewed by the workshop’s program committee. Submissions will be evaluated on technical merit, empirical evaluation, and compatibility with the workshop focus. Evaluation on real robotic systems is highly encouraged.
Work that has already appeared or is scheduled to appear in a journal, workshop, or conference (including NeurIPS 2019) must be significantly extended to be eligible. Work that has only been published as academic preprint (r.g. arxiv) can be submitted.
Invited Speakers
Manuela Maria Veloso (J.P. Morgan AI Research / Carnegie Mellon University)
Dieter Fox (NVIDIA / University of Washington)
Takayuki Osa (Kyushu Institute of Technology)
Angela Schoellig (University of Toronto)
Nima Fazeli (University of Michigan, Ann Arbor)
Edward Johns (Imperial College London)
Organisers
Sanket Kamthe (Imperial College London)
Kate Rakelly (University of California, Berkeley)
Markus Wulfmeier (Google DeepMind)
Roberto Calandra (Facebook AI Research)
Danica Kragic (Royal Institute of Technology, KTH)
Stefan Schaal (Google)
Vancouver Convention Center, Vancouver, Canada
13th or 14th December 2019
http://www.robot-learning.ml/2019/
The growing capabilities of learning-based methods in control and robotics have precipitated a shift in the design of software for autonomous systems. Recent successes fuel the hope that robots will increasingly perform varying tasks working alongside humans in complex, dynamic environments. However, the application of learning approaches to real-world robotic systems has been limited because real-world scenarios introduce challenges not arising in simulation. We focus on three broad challenges that currently preclude the deployment of machine learning methods on real systems:
Most current machine learning methods rely on large quantities of labeled data. While raw sensor data is available at high rates, the required variety is hard to obtain and the human effort to annotate or design reward functions is an even larger burden.
Algorithms must guarantee some measure of safety and robustness to be deployed in real systems that interact with property and people. Instantaneous reset mechanisms, as common in simulation to recover from even critical failures, present a great challenge to real robots.
The real world is significantly more complex and varied than curated datasets and simulations. Successful approaches must scale to this complexity, be able to adapt to novel situations and recover from mistakes.
We invite submissions that focus on tackling these challenges resulting from operation in the real world. We will encourage submissions that experiment on physical systems, and specifically consider algorithmic developments aimed at tackling the challenges presented by physical systems. A non-exhaustive list of relevant topics is:
transfer and multitask learning
explicit methods for planning
uncertainty quantification
safety and robustness
simulation-to-real transfer and domain adaptation
model learning
Deadlines
Submission Deadline: 9th September (AOE)
Acceptance Notification: 1st October (AOE)
Camera-Ready Deadline: 1st December (AOE)
Format
Manuscripts should be a short research paper of at most 4 pages long (excluding references) in the LaTeX format defined here. The main text should include all text and figures, and should adequately describe the work, its contributions, and its limitations. Manuscripts must be anonymized.
Please submit your extended abstract via https://cmt3.research.microsoft.com/NEURIPSWRL2019 by the deadline given above.
Contact neuripswrl2019@robot-learning.ml
Selection Criteria
All submissions will be peer reviewed by the workshop’s program committee. Submissions will be evaluated on technical merit, empirical evaluation, and compatibility with the workshop focus. Evaluation on real robotic systems is highly encouraged.
Work that has already appeared or is scheduled to appear in a journal, workshop, or conference (including NeurIPS 2019) must be significantly extended to be eligible. Work that has only been published as academic preprint (r.g. arxiv) can be submitted.
Invited Speakers
Manuela Maria Veloso (J.P. Morgan AI Research / Carnegie Mellon University)
Dieter Fox (NVIDIA / University of Washington)
Takayuki Osa (Kyushu Institute of Technology)
Angela Schoellig (University of Toronto)
Nima Fazeli (University of Michigan, Ann Arbor)
Edward Johns (Imperial College London)
Organisers
Sanket Kamthe (Imperial College London)
Kate Rakelly (University of California, Berkeley)
Markus Wulfmeier (Google DeepMind)
Roberto Calandra (Facebook AI Research)
Danica Kragic (Royal Institute of Technology, KTH)
Stefan Schaal (Google)
Journal Promotion
|
| Acta Koreana (Acta Koreana) |
|
| Acta Via Serica (AVS) |
|
| Computers and Concrete (CAC) |
|
| Journal of Information Processing Systems (JIPS) |
|
| Journal of Internet Computing and Services (KSII - JICS) |
|
| Journal of Smart Tourism (Smart Tourism) |
|
| Membrane and Water Treatment (MWT) |
|
| Wind and Structures, An International Journal (Wind and Structures) |
MANUSCRIPTLINK © 2015 -
