Presentation is loading. Please wait.

Presentation is loading. Please wait.

Planning for Persistent Autonomy: Where are we struggling ?

Similar presentations


Presentation on theme: "Planning for Persistent Autonomy: Where are we struggling ?"— Presentation transcript:

1 Planning for Persistent Autonomy: Where are we struggling ?
Daniele Magazzeni King’s College London

2 Artificial Intelligence Planning Group at King’s
We have a rich portfolio of planning for real applications, with companies and organisations: Autonomous Underwater Vehicles Energy Technology Autonomous Drones and UAVs Ocean Liners Multiple Battery System Management Hybrid Vehicles Smart Buildings Air Traffic Control and Plane Taxiing Urban Traffic Control

3 Planning with Robots Planning for Persistent Underwater Autonomy
Policy Learning for Autonomous Feature Tracking Autonomous maintenance of submerged oil & gas infrastructures EU Project PANDORA Policy Learning for Autonomous Feature Tracking.  Autonomous Robots. (2015) Toward Persistent Autonomous Intervention in a Subsea Panel.  Autonomous Robots. (2016) Opportunistic Planning in Autonomous Underwater Missions.  IEEE Transactions on Automation Science and Engineering. (2017)

4 Planning with Robots Robot interacting with children in a toy cleaning scenario -localisation and navigation in a crowded and changing scene  -iterative task planning in an open world -engaging with multiple users in a dynamic collaborative task Robotics Receptionist at King’s College (with Elizabeth Sklar and Simon Parsons) Goal: to deliver an advanced yet flexible space autonomous software framework/system suitable for single and/or collaborative space robotic means/missions

5 Focus of Our Research Rich planning models Validation Integration
We are pushing the research on planning with hybrid systems PDDL+ modelling Planners (UPMurphi, DiNO, SMTPlan+) Policy learning framework Planning with external solvers Validation We explore the links between planning and verification Plan validation (VAL) Plan robustness evaluation Domain validation Integration Planning with ROS

6 Agnostic about the planning system
Modular Open source and free

7 Domain/Plan Correctness/Robustness
I believe that in planning we are too optimistic about the assumptions we can make. Q1: what are reasonable assumptions we can make when writing our domains? (relocation, precise sensing, actuator precision) Plans are correct-by-construction, modulo the correctness of the model. Q2: can we do domain validation, and what does it mean in robotics domain? In persistent autonomy, plan validity is affected by temporal uncertainty due to uncertain and dynamic environment. Q3: how can we evaluate plan temporal robustness? Planning community is making great progress in handling very rich planning models (PDDL+, external solver, semantic attachments) Q4: how can we leverage rich domain modelling to model robot dynamics? Do robotics people think it's important to model dynamics in the planning model?

8 What should I plan for ? We often (always?) assume to have goals. I'd like the robot to collaborate in deciding upon its own goals. Based on: -HRI -Curiosity and exploration -Motivations -Need for recovering. Problem awareness -Improving its own domain model. (I'll get back in one hour and I want to see a more concrete domain file). Q5: are there other factors the Robot should check for deciding goals? Q6: how are we doing (really) with this issue?

9 Human-Robot Interaction (not the standard one…)
In many cases, policies request humans to approve plans before execution: Q7: how can we make plans clear to humans? (not PDDL.. , non domain-specific approach, instruction graphs) If the operator cannot approve the plan, perhaps he/she could approve a slightly different plan. Q8: how can we effectively handle plan execution with human interaction? Humans can decide to take less/more risk (e.g., for getting less/more reward) Q9: should we be generating sets of plans, rather than a single plan?

10 Integration Good progress so far, but still a lot to do. Q10: where should we focus? When planning for long-horizon missions, scalability is a huge issue. Q11: is it possible to create a model/planning solution that is detailed, but becomes gradually abstract further into the future? Can such a solution be integrated, and handled at execution time? Q12: can we share benchmarks and data sets?

11 Daniele Magazzeni Thank you! BTW: we are hiring!

12 (non-exhaustive) list…
Q1: what are reasonable assumptions we can make when writing our domains? Q2: can we do domain validation, and what does it mean in robotics domain? Q3: how can we evaluate plan temporal robustness? Q4: how can we leverage rich domain modelling to model robot dynamics? Do robotics people think it's important to model dynamics in the planning model? Q5: are there other factors the Robot should check for deciding goals? Q6: how are we doing (really) with this issue? Q7: how can we make plans clear to humans? (not PDDL.. , non domain-specific approach, instruction graphs) Q8: how can we effectively handle plan execution with human interaction? Q9: should we be generating sets of plans, rather than a single plan? Q10: where should we focus? Q11: is it possible to create a model/planning solution that is detailed, but becomes gradually abstract further into the future? Can such a solution be integrated, and handled at execution time? Q12: can we share benchmarks and data sets?


Download ppt "Planning for Persistent Autonomy: Where are we struggling ?"

Similar presentations


Ads by Google