Research Workshop of the Israel Science Foundation
PlanRob - Workshop on Planning and Robotics
Topics and Objectives
Robotics is one of the most appealing and natural applicative area for the Planning and Scheduling (P&S) research activity, however such a natural interest seems not reflected in an equally important research production for the Robotics community. In this perspective, the aim of the PlanRob workshop is twofold. On the one hand, this workshop would constitute a fresh impulse for the ICAPS community to develop its interests and efforts towards this challenging research area. On the other hand, it aims at attracting representatives from the Robotics community to discuss their challenges related to planning for autonomous robots (deliberative, reactive, continuous planning and execution etc.) as well as their expectations from the P&S community.
The PlanRob workshop aims at constituting a stable, long-term forum on relevant topics concerned with the interactions between Robotics and P&S communities where researchers could discuss about the opportunities and challenges of P&S when applied to Robotics.
Started during ICAPS 2013 in Rome (Italy) and followed by the second edition at ICAPS 2014 in Portsmouth (NH, USA), the PlanRob WS series (http://pst.istc.cnr.it/planrob/) has gathered very good feedback from the P&S community which is also confirmed by the organisation of a specific Robotics Track at ICAPS 2014 chaired by Felix Ingrand and Leslie Kaelbling (http://icaps14.icaps-conference.org/specialtracks/robotics.html) and also this year at ICAPS 2015 chaired by Reid Simmons and Micheal Beetz (https://icaps15.icaps-conference.org/tracks/robotics.html).
Sponsors
PlanRob 2015 is partially supported by the FourByThree project (http://www.fourbythree.euc - EU H2020 G.A. FoF- 637095) and the SHERPA project (http://www.sherpa-project.eu EU FP7 G.A. ICT-600958).
Proceedings
The full PLANROB proceedings are available as a pdf file [file has been updated -June 14).
Schedule
DAY 1 - June 7, 2015 (Room E)
13:50-14:00 | PlanRob WS Introduction |
14:00-15:00 | Keynote: Reid Simmons (Carnegie Mellon University, USA)Robust Autonomy |
Session: Context and Constraint Reasoning | |
15:00-15:30 |
Solomon Eyal Shimony, Gera Weiss and Liat Cohen Estimating the Probability of Meeting a Deadline in Hierarchical Plans |
15:30-16:00 | Coffee Break |
Session: Task, motion and path planning | |
16:00-16:30 |
Jonathan Ferrer-Mestres, Guillem Francès and Hector Geffner Planning with State Constraints and its Application to Combined Task and Motion Planning |
16:30-17:00 | Weifeng Chen and Martin Müller
Continuous Arvand: Motion Planning with Monte Carlo Random Walks |
17:00-17:30 |
Ty Nguyen and Tsz-Chiu Au Motion Planning for Arrival Time and Velocity Requirements on Non-homogeneous Roads |
17:30-18:00 |
Roi Yehoshua, Noa Agmon and Gal Kaminka Frontier-Based RTDP: A New Approach to Solving the Robotic Adversarial Coverage Problem |
Session: Benchmarking | |
18:00-18:30 |
Pablo Muñoz, Amedeo Cesta, Andrea Orlandini and Maria D. R-Moreno A Framework for Performance Assessment of Autonomous Robotic Controllers |
18:30-19:00 |
Tim Niemueller, Gerhard Lakemeyer and Alexander Ferrein The RoboCup Logistics League as a Benchmark for Planning in Robotics |
DAY 2 - June 8, 2015 (Room B)
08:55-09:00 | PlanRob WS Introduction 2 |
09:00-10:00 | Keynote: Steve Chien (NASA JPL) Using Constraint-based Search to Schedule Science Campaigns for the Rosetta Orbiter |
Session: Context and Constraint Reasoning | |
10:00-10:30 |
Andreas Hofmann and Paul Robertson Active Perception: Using Goal Context to Guide Sensing and Other Actions |
10:30-11:00 | Coffee Break |
11:00-11:30 |
Michael Cashmore, Maria Fox, Derek Long, Daniele Magazzeni, Bram Ridder and Francesco Maurelli Dynamically Extending Planning Models using an Ontology |
Session: Planning and Execution | |
11:30-12:00 |
Dylan O'Ceallaigh and Wheeler Ruml Metareasoning for Concurrent Planning and Execution |
12:00-12:30 |
Breelyn Kane Styler and Reid Simmons Robust Efficient Robot Planning through Varying Model Fidelity |
12:30-13:00 |
Enrique Fernandez Gonzalez, Erez Karpas and Brian Williams Mixed Discrete-Continuous Heuristic Generative Planning based on Flow Tubes (extended version) |
13:00-14:00 | Lunch Break |
Session: Multi Robot framework | |
14:00-14:30 |
Gal Kaminka No robot is an island, no team an archipelago: Plan execution for cooperative multi-robot teams |
14:30-15:00 |
Mark Roberts, Swaroop Vattam, Ron Alford, Bryan Auslander, Tom Apker, Benjamin Johnson and David Aha Goal Reasoning to Coordinate Robotic Teams for Disaster Relief |
Session: Human-Robot Interaction | |
15:00-15:30 |
Tathagata Chakraborti, Gordon Briggs, Kartik Talamadupula, Matthias Scheutz, David Smith and Subbarao Kambhampati Planning for Serendipity - Altruism in Human-Robot Cohabitation |
15:30-16:00 | Coffee Break |
16:00-16:30 |
Tathagata Chakraborti, Tony Zhang, David Smith and Subbarao Kambhampati Planning with Stochastic Resource Profiles: An Application to Human-Robot Co-habitation |
16:30-17:00 |
Mouaddib Abdel-Illah, Laurent Jeanpierre and Shlomo Zilberstein Handling Advice in MDPs for Semi-Autonomous Systems |
17:00-17:30 | Panel Session |
Keynote Information
Reid Simmons
Robust Autonomy
Abstract: The keynote will present some recent results on robust autonomy as well as a quick survey of planning & execution and robot architectures.
Bio: Reid Simmons is a Research Professor and Associate Director for Education at the Carnegie Mellon University.
His research interests focus on developing reliable, highly autonomous systems (especially mobile robots) that operate in rich, uncertain environments. The goal is to create intelligent systems that can operate autonomously for long periods of time in unstructured, natural environments. This necessitates robots that can plan, effectively reason about uncertainty, diagnose and recover from unanticipated errors, and reason about their limitations. In particular, He is interested in architectures for autonomy that combine deliberative and reactive behavior, reliable execution monitoring and error recovery, multi-robot coordination, probabilistic and symbolic planning, formal verification of autonomous systems, and human-robot social interaction.
Steve Chien
Using Constraint-based Search to Schedule Science Campaigns for the Rosetta Orbiter
Abstract: In August 2014, Rosetta (http://blogs.esa.int/rosetta/) entered orbit around the comet Churyumov-Gerasimenko. Rosetta, a European Space Agency led mission to explore the comet Churyumov-Gerasimenko, is the first mission to deploy a soft lander to a comet, and to escort a comet for an extended period (over one year).
But Rosetta is also a pathfinding space mission from the perspective of Operations, Computer Science, and Artificial Intelligence in it’s usage of the ASPEN Artificial Intelligence planning and scheduling software for early to mid-range science activity scheduling.
In my talk I first briefly discuss comets and their importance in understanding the evolution of our solar system and life on Earth. Second, I describe elements of the multi- disciplinary Rosetta science planning process which incorporates diverse science, geometric, engineering, and resource constraints. Next, I describe the constraint-driven scheduling automation and how AI has much to offer not only in schedule generation, but in constraint enforcement, problem and constraint analysis, and in iterative schedule refinement. Finally, I will discuss prospects for onboard decision-making for future cometary missions highlighting robotics challenges related to planning and scheduling.
Bio: Dr. Steve Chien is Head of the Artificial Intelligence Group and Senior Research Scientist at the Jet Propulsion Laboratory, California Institute of Technology where he leads efforts in autonomous systems for space exploration.
Dr. Chien has received numerous awards for his research in space autonomous systems: he has been awarded three NASA Medals in 1997, 2000, and 2007; he is a four time honoree in the NASA Software of the Year competition; and in 2011 he was awarded the innaugural AIAA Intelligent Systems Award. He has led the deployment of ground and flight autonomy software to numerous missions including the Autonomous Sciencecraft on Earth Observing One, the WATCH software to the Mars Exploration Rovers, the Earth Observing Sensorweb, and the IPEX Cubesat. He is currently leading the deployment of ASPEN for scheduling science observations for the Rosetta mission, an ESA-led mission to explore the comet Churyumov-Gerasimenko.
The ASPEN deployment to Rosetta is a joint JPL-ESA effort including: Steve Chien, Gregg Rabideau, Daniel Tran, Martina Troesch, Joshua Doubleday (JPL/Caltech/NASA) and Federico Nespoli, Miguel Perez Ayucar, Marc Costa Sitja, Claire Vallat, Bernhard Geiger, Nico Altobelli, Manuel Fernandez, Fran Vallejo, Rafael Andres, Michael Kueppers (ESA).
Accepted Papers
- Solomon Eyal Shimony, Gera Weiss and Liat Cohen
Estimating the Probability of Meeting a Deadline in Hierarchical Plans - Roi Yehoshua, Noa Agmon and Gal Kaminka
Frontier-Based RTDP: A New Approach to Solving the Robotic Adversarial Coverage Problem - Michael Cashmore, Maria Fox, Derek Long, Daniele Magazzeni, Bram Ridder and Francesco Maurelli
Dynamically Extending Planning Models using an Ontology - Pablo Muñoz, Amedeo Cesta, Andrea Orlandini and Maria D. R-Moreno
A Framework for Performance Assessment of Autonomous Robotic Controllers - Andreas Hofmann and Paul Robertson
Active Perception: Using Goal Context to Guide Sensing and Other Actions - Jonathan Ferrer-Mestres, Guillem Francès and Hector Geffner
Planning with State Constraints and its Application to Combined Task and Motion Planning - Ty Nguyen and Tsz-Chiu Au
Motion Planning for Arrival Time and Velocity Requirements on Non-homogeneous Terrains - Weifeng Chen and Martin Müller
Continuous Arvand: Motion Planning with Monte Carlo Random Walks - Mark Roberts, Swaroop Vattam, Ron Alford, Bryan Auslander, Tom Apker, Benjamin Johnson and David Aha
Goal Reasoning to Coordinate Robotic Teams for Disaster Relief - Gal Kaminka.
No robot is an island, no team an archipelago: Plan execution for cooperative multi-robot teams - Dylan O'Ceallaigh and Wheeler Ruml
Metareasoning for Concurrent Planning and Execution - Tim Niemueller, Gerhard Lakemeyer and Alexander Ferrein
The RoboCup Logistics League as a Benchmark for Planning in Robotics - Breelyn Kane Styler and Reid Simmons
Robust Efficient Robot Planning through Varying Model Fidelity - Enrique Fernandez Gonzalez, Erez Karpas and Brian Williams
Mixed Discrete-Continuous Heuristic Generative Planning based on Flow Tubes (extended version) - Tathagata Chakraborti, Tony Zhang, David Smith and Subbarao Kambhampati
Planning with Stochastic Resource Profiles: An Application to Human-Robot Co-habitation - Tathagata Chakraborti, Gordon Briggs, Kartik Talamadupula, Matthias Scheutz, David Smith and Subbarao Kambhampati
Planning for Serendipity - Mouaddib Abdel-Illah, Laurent Jeanpierre and Shlomo Zilberstein
Handling Advice in MDPs for Semi-Autonomous Systems