Due to AAAI SS21 conversion to virtual format, paper submission deadline is extended to January 15, 2021

Dear Roboticists,

we would like to invite you to participate in our AAAI Spring Symposium Machine Learning for Mobile Robot Navigation in the Wild (https://sites.google.com/utexas.edu/ml4nav/), which will take place March 22-24 at Stanford University in Palo Alto, California, USA. We are also seeking related contributions in the form of six-page full paper and two-page abstract, and industrial participants. The submission deadline is November 8th. AAAI EasyChair site submission link can be found at https://easychair.org/conferences/?conf=sss21. For details, please see the following Call for Participation (https://docs.google.com/document/d/1WHmfNDilpvVieK1JbaTDy6SCNbmuREdQN7YEZu3OU64/edit?usp=sharing):

Call for Participation

The Machine Learning for Mobile Robot Navigation in the Wild Symposium in AAAI 2021 SSS will take place March 22-24 at Stanford University in Palo Alto, California, USA. The 2.5-day symposium will consist of invited talks, technical presentations, spotlight posters, robot demonstrations, industry spotlights, breakout sessions, and interactive panel discussions. 

Decades of research efforts have enabled classical navigation systems to move robots from one point to another, observing system and environmental constraints. However, navigation outside a controlled test environment, i.e., navigation in the wild, remains a challenging problem: an extensive amount of engineering is necessary to enable robust navigation in a wide variety of environments, e.g., to calibrate perception or to fine-tune navigational parameters; classical map-based navigation is usually treated as a pure geometric problem, without considering other sources of information, e.g., terrain, risk, social norms, etc. 

On the other hand, advancements in machine learning provide an alternative avenue to develop navigation systems, and arguably an “easier” way to achieve navigation in the wild. Vision input, semantic information, terrain stability, social compliance, etc. have become new modalities of world representations to be learned for navigation beyond pure geometry. Learned navigation systems can also largely reduce engineering effort in developing and tuning classical techniques. However, despite the extensive application of machine learning techniques on navigation problems, it still remains a challenge to deploy mobile robots in the wild in a safe, reliable, and trustworthy manner. 

In this symposium, we focus on navigation in the wild as opposed to navigation in a controlled, well-engineered, sterile environment like labs or factories. In the wild, mobile robots may face a variety of real-world scenarios, other robot or human companions, challenging terrain types, unstructured or confined environments, etc. This symposium aims at bringing together researchers who are interested in using machine learning to enable mobile robot navigation in the wild and to provide a shared platform to discuss learning fundamental navigation (sub)problems, despite different application scenarios. Through this symposium, we want to answer questions about why, where, and how to apply machine learning for navigation in the wild, summarize lessons learned, identify open questions, and point out future research directions. 

Symposium URL: https://sites.google.com/utexas.edu/ml4nav/

Organizing Committee:

Xuesu Xiao (Symposium Chair), The University of Texas at Austin, Email: xiao@cs.utexas.edu

Harel Yedidsion, The University of Texas at Austin, Email: harel@cs.utexas.edu

Reuth Mirsky, The University of Texas at Austin, Email: reuth@cs.utexas.edu

Justin Hart, The University of Texas at Austin, Email: hart@cs.utexas.edu

Peter Stone, The University of Texas at Austin, Sony AI, Email: pstone@cs.utexas.edu

Ross Knepper, Cornell University, Email: ross.knepper@gmail.com

Hao Zhang, Colorado School of Mines, Email: hzhang@mines.edu

Jean Oh, Carnegie Mellon University, Email: jeanoh@cmu.edu

Davide Scaramuzza, University of Zurich, ETH Zurich, Email: sdavide@ifi.uzh.ch

Vaibhav Unhelkar, Rice University, Email: vaibhav.unhelkar@rice.edu

Submission Instructions: 

Full papers of up to six pages and abstract papers of up to two pages are sought in the following topic areas: 

·         Learning for social navigation

·         Learning for terrain-based navigation

·         Learning for vision-based navigation

·         Learning for interactive navigation

·         Representation learning for navigation 

·         Sim2real for navigation

·         Zero-shot path planning

·         Learning for navigation in unstructured or confined environments

·         Reinforcement learning for navigation in the wild

·         Imitation learning for navigation in the wild

·         Active learning for navigation in the wild

·         Lifelong/continual learning for navigation in the wild

·         Geometric methods for learning navigation 

·         Real-world validation of learning for navigation

·         Navigation problems, benchmarks, and metric

All contributions should be submitted electronically via AAAI EasyChair site (https://easychair.org/conferences/?conf=sss21). The submission format is the standard double-column AAAI Proceedings Style. The author kit can be found at https://www.aaai.org/Publications/Templates/AuthorKit21.zip. The review process is single-blind.

We also welcome participation of industrial partners, who are encouraged to bring their mobile robots to the site and share their research and engineering expertise with all participants of the symposium. For potential industrial partners, please reach out to the organizing committee for more details. 

For questions, please contact the Symposium Chair

Dr. Xuesu Xiao, 

Department of Computer Science

The University of Texas at Austin

2317 Speedway, Austin, Texas 78712-1757 USA

+1 (512) 471-9765

xiao@cs.utexas.edu

https://www.cs.utexas.edu/~xiao/