• Submission deadline: 31 May, 2021 UTC-12
  • Notification: 30 June, 2021

PlanRob

9th ICAPS Workshop on Planning and Robotics


Topics and Objectives

AI Planning & Scheduling (P&S) methods are key to enabling intelligent robots to perform autonomous, flexible, and interactive behaviors. Researchers in the P&S community have continued to develop approaches and produce planners, representations, as well as heuristics that robotics researchers can make use of. However, there remain numerous challenges complicating the uptake, use and successful integration of P&S technology in robotics, many of which have been addressed by robotics researchers with novel solutions. Strong collaboration and synergy between researchers in both communities is vital to the continued growth of the fields in a way that provide mutual benefits to the two communities. To foster this, the PlanRob workshop aims to provide a stable, long-term forum (having been held annually at ICAPS since 2013) where researchers from both the P&S and Robotics communities can openly discuss relevant issues, research and development progress, future directions and open challenges related to P&S when applied to Robotics. In addition to the usual paper submissions, the workshop’s format naturally lends itself to preliminary results, position papers as well as to work focused on challenges in using and integrating planners in robotics systems.

Topics of interest include (but are not limited to) the following:

  • real-world planning applications for autonomous and intelligent robots;
  • optimizing behavior in large scale automated or semi-automated systems;
  • integrated planning and execution in robotic architectures;
  • planning domain representations for robotics applications;
  • P&S methods for optimization and adaptation in robotics;
  • mission, path, and motion planning for robots;
  • planning and coordination methods for multi-robot teams;
  • mixed-initiative planning and sliding autonomy for robotic systems;
  • human-aware planning and execution in human-robot interaction;
  • adversarial action planning in competitive robotic domains;
  • formal methods for robot planning and control;
  • challenges and solutions in using P&S technology in robotics;
  • open problems for P&S in robotics,
  • benchmark planning domains for robots.

PLANROB 2021 PROGRAM

The collection of accepted papers can be downloaded here.

August 4th (GMT Time)
10:0010:10Intro
Task & Motion Planning 1
10:1010:3524. Combining Task and Motion Planning through Rapidly-exploring Random Trees. Riccardo Caccavale and Alberto Finzi
10:3511:0014. Limits and Possibilities of Multi Goal Task Motion Planning. Stefan Edelkamp
11:0011:2513. Extended Task and Motion Planning of Long-horizon Robot Manipulation. Tianyu Ren, Georgia Chalvatzaki and Jan Peters
11:2511:5011. Multi-objective Path-based D* Lite. Zhongqiang Ren, Sivakumar Rathinam and Howie Choset
11:5012:10Break
Space and Planetary Rover
12:1012:3512. MarsExplorer: Exploration of Unknown Terrains via Deep Reinforcement Learning and Procedurally Generated Environments. Dimitrios Koutras, Athanasios Kapoutsis, Angelos Amanatiadis and Elias Kosmatopoulos
12:3513:008. A Sampling-Based Optimization Approach to Handling Environmental Uncertainty for a Planetary Lander. Connor Basich, Daniel Wang, Joseph Russino, Steve Chien and Shlomo Zilberstein
13:0013:2521. Deliberation and Plan Execution for Intra-vehicle Robotic Activities in Space. J. Benton, Abiola Akanni and Robert Morris
13:2513:45Break
Cognitive and Trustworthy Robotics
13:4514:1017. Non-monotonic Logical Reasoning Guiding Axiom Induction from Deep Networks for Transparent Decision Making in Robotics. Mohan Sridharan and Tiago Mota
14:1014:3525. Two-layered Architecture for Telepresence Robots: Combining Personalization and Reactivity. Gloria Beraldo, Riccardo De Benedictis, Amedeo Cesta and Gabriella Cortellessa
14:3515:0019. Trust-Aware Planning:Modeling Trust Evolution in Longitudinal Human-Robot Interaction. Zahra Zahedi, Mudit Verma, Sarath Sreedharan and Subbarao Kambhampati
15:0016:00Keynote by Peter Stone

August 5th
Planning with Uncertainty
10:0010:253. An Interactive Approach for the Analysis and Shielding of Partially Observable Monte Carlo Planning Policies. Giulio Mazzi, Giovanni Bagolin, Alberto Castellini and Alessandro Farinelli
10:2510:504. Combining Temporal and Probabilistic Planning for Robots Operating in Extreme Environments. Jun Hao Alvin Ng, Yaniel Carreno, Yvan Petillot and Ron Petrick
10:5011:157. Probabilistic Plan Legibility with Off-the-shelf Planners. Michele Persiani and Thomas Hellstrom
11:1511:4023. Compiling Contingent Planning into Temporal Planning for Robust AUV Deployments. Yaniel Carreno, Yvan Petillot and Ron Petrick
11:4012:00Break
Task & Motion Planning 2
12:0012:2515. SM2P: Towards a Robust Co-Pilot System for Helicopter EMS. Ian Mallet, Marcus Hoerger, Surabhi Gupta, Nisal Jayalath, Felipe Trevizan, Andrew Hunt, Hanna Kurniawati and Christophe Guettier
12:2512:5020. Learning Sampling Distributions for Efficient High-Dimensional Motion Planning. Naman Shah, Abhyudaya Srinet and Siddharth Srivastava
12:5013:1518. Benchmarking Sampling-based Motion Planning Pipelines for Wheeled Mobile Robots. Eric Heiden, Luigi Palmieri, Leonard Bruns, Kai O. Arras, Gaurav S. Sukhatme and Sven Koenig
13:1513:406. Construction Site Automation: Open Challenges for Planning and Robotics. Paolo Forte, Anna Mannucci, Henrik Andreasson and Federico Pecora
13:4014:00Break
Planning and Execution
14:0014:252. An Action Interface Manager for ROSPlan. Stefan-Octavian Bezrucav, Gerard Canal, Michael Cashmore and Burkhard Corves
14:2514:5010. Real-time Planning and Execution for Industrial Operations. Filip Dvorak
14:5015:1516. State-Temporal Decoupling of Multi-Agent Plans under Limited Communication. Yuening Zhang, Jingkai Chen, Eric Timmons, Marlyse Reeves and Brian Williams
15:1515:40Closing

Keynote Talk

On August 4th 3pm GMT by Dr. Peter Stone

Title: Task Planning and Learning for General-Purpose Service Robots
Abstract:

Despite recent progress in the capabilities of autonomous robots, especially learned robot skills, there remain significant challenges in building robust, scalable, and general-purpose systems for service robots. Our research aims to answer the question "How can symbolic reasoning and machine learning methods be combined to create general-purpose service robots that reason about high-level actions and adapt to the real world?"

We approach this question from two directions. First, we introduce planning algorithms that adapt to the environment using machine learning and exchanging knowledge with other agents. These algorithms allow robots to plan in open-world scenarios, to plan around other robots while avoiding conflicts and realizing synergies, and to adapt plans by learning action costs throughout executions in the real world. Second, we develop reinforcement learning (RL) methods for service robot systems. These methods address the challenges of maximizing the long-term average reward in continuing tasks, as well as improving sample efficiency by leveraging reasoning and planning via reward shaping. Taken together, our research makes significant strides towards solving the grand challenge of creating general-purpose service robots.

[Based on joint work with Yuqian Jiang and others]

Important Dates

Paper submission: May 31, 2021
Notification of acceptance: June 30, 2021
Camera-ready version due: July 15, 2021
Workshop Date: August 2-6, 2021

The reference time-zone for all deadlines is UTC-12: Your submissions will be on time so long as there is still some place in the world where the deadline has not yet passed.

Submissions

There are two types of submissions: short position papers and regular papers. Position papers are a maximum of four pages long while regular papers may be up to ten pages long. Papers may have an additional page containing references. Regular papers may be scheduled with more time in the final program. A poster session may be considered to provide a further presentation opportunity.

The guidelines for formatting are the same as is used for ICAPS 2021 papers (typeset in the AAAI style as described at: http://www.aaai.org/Publications/Author/author.php), but with the AAAI copyright removed. The papers must be submitted in PDF format via the EasyChair system (https://easychair.org/conferences/?conf=planrob2021).

Please note that papers under review (e.g. which have been submitted to IJCAI-2021) are also welcome, however, in order to avoid potential conflicts, these manuscripts should be prepared as anonymous submissions for a double blind reviewing process.

Accepted papers will be published on the workshop’s website.

The organizers are investigating the availability of journal editors in order to invite a selection of accepted papers from the workshop to a special issue or post-proceedings volume.

Organization

  • Iman Awaad, Hochschule Bonn-Rhein-Sieg University of Applied Sciences, iman.awaad at h-brs.de
  • Alberto Finzi, Università di Napoli "Federico II", alberto.finzi at unina.it
  • AndreA Orlandini, Institute of Cognitive Sciences and Technologies (ISTC-CNR), andrea.orlandini at istc.cnr.it

The ICAPS PlanRob Workshop is partially supported by TAILOR "Foundations of Trustworthy AI - Integrating Reasoning, Learning and Optimization", a project funded by the European Commissione (EU H2020 ICT-48 G.A. 952215).