ScottyActivity: Mixed Discrete-Continuous Planning with Convex Optimization

@article{FernndezGonzlez2018ScottyActivityMD,
  title={ScottyActivity: Mixed Discrete-Continuous Planning with Convex Optimization},
  author={Enrique Fern{\'a}ndez-Gonz{\'a}lez and Brian Charles Williams and Erez Karpas},
  journal={J. Artif. Intell. Res.},
  year={2018},
  volume={62},
  pages={579-664}
}
The state of the art practice in robotics planning is to script behaviors manually, where each behavior is typically generated using trajectory optimization. However, in order for robots to be able to act robustly and adapt to novel situations, they need to plan these activity sequences autonomously. Since the conditions and effects of these behaviors are tightly coupled through time, state and control variables, many problems require that the tasks of activity planning and trajectory… 

Optimal mixed discrete-continuous planning for linear hybrid systems

This paper presents a hybrid automaton planning formalism and proposes an optimal approach that encodes this planning problem as a Mixed Integer Linear Program (MILP) by fixing the action number of automaton runs and shows an extension of the approach for reasoning over temporally concurrent goals.

Minimum Time Validation for Hybrid Task Planning

This paper addresses the minimum time problem for a second-order system with quadratic drag, under state (velocity) and control (acceleration) constraints and proves the optimality of the Pontryagin Maximum Principle.

Motion Planning Under Uncertainty with Complex Agents and Environments via Hybrid Search

Three approaches to modeling trajectory risk are discussed: a CDF-based approach, a sampling-based collocation method, and an algorithm named Shooting Method Monte Carlo that allow computation of trajectory risk with more complex environments, agent dynamics, geometries, and models of uncertainty than past approaches.

Cyber-Physical Planning: Deliberation for Hybrid Systems with a Continuous Numeric State

This work proposes techniques to refine a high-level plan into a continuous state trajectory using a nonlinear optimization problem with constraints that can encode the intrinsic limitations and dynamics of the system as well as the rules for its continuous control.

Minimum Time Optimal Control of Second Order System With Quadratic Drag and State Constraints

This work addresses the minimum time problem for a second-order system with quadratic drag, under state (velocity) and control (acceleration) constraints, and the optimality is proven using the Pontryagin Maximum Principle.

Gradient-Based Mixed Planning with Discrete and Continuous Actions

A gradient-based framework to simultaneously optimize continuous parameters and actions of candidate plans and a heuristic module to estimate the best plan candidate to transit initial state to the goal based on relaxation is proposed.

RNNs Based Planning with Discrete and Continuous Actions

  • Computer Science
  • 2020
This paper proposes a novel algorithm framework based on recurrent neural networks for mixed planning with discrete and continuous actions in non-convex domains as a gradient descent search problem.

PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning

This work provides domain-independent algorithms that reduce PDDLStream problems to a sequence of finite PDDL problems and introduces an algorithm that dynamically balances exploring new candidate plans and exploiting existing ones to solve tightly-constrained problems.

A Hierarchical Planner based on Set-theoretic Models: Towards Automating the Automation for Autonomous Systems

A set-theoretic approach is used to model declarative and procedural knowledge which allows for flexible hierarchies of planning tasks and presents two use-cases of an autonomous manufacturing system to highlight the capabilities of the system.

Multi-Modal Motion Planning Using Composite Pose Graph Optimization

The resulting motion planning algorithm optimizes the multi-modal trajectory, including the location of mode transitions, and is guided by the pose graph optimization process to eliminate unnecessary transitions, enabling efficient discovery of optimized mode sequences from rough initial guesses.

References

SHOWING 1-10 OF 56 REFERENCES

Generative multi-robot task and motion planning over long horizons

Scotty is presented, a planning system for hybrid activity and trajectory planning problems that can solve a broad class of expressive robotic planning problems by supporting convex quadratic constraints on state variables and control variables that are jointly constrained and that affect multiple state variables simultaneously.

Mixed Discrete-Continuous Planning with Convex Optimization

While naive formulations of consistency checks are not convex and do not scale, cqScotty uses an efficient convex formulation, in the form of a Second Order Cone Program (SOCP), that is very fast to solve and demonstrates the scalability of the approach on three new realistic domains.

Mixed Discrete-Continuous Heuristic Generative Planning Based on Flow Tubes

Scotty is introduced, a mixed discrete-continuous generative planner that finds the middle ground between these two temporal planners, and exploits the expressivity of flow tubes, which compactly encapsulate continuous effects, and the performance of heuristic forward search.

Logic-Geometric Programming: An Optimization-Based Approach to Combined Task and Motion Planning

This work proposes to formulate the problem of sequential robot manipulation holistically as a 1st- order logic extension of a mathematical program: a non-linear constrained program over the full world trajectory where the symbolic state-action sequence defines the (in-)equality constraints.

Generative Planning for Hybrid Systems Based on Flow Tubes

A novel approach to solving the generative planning problem for hybrid systems, involving both continuous and discrete actions, is described, including a hybrid planner that determines a series of discrete and continuous actions that achieve the mission goals.

Kongming: a generative planner for hybrid systems with temporally extended goals

This thesis has successfully demonstrated controlling an AUV in the Atlantic ocean using mission scripts solely generated by Kongming, a novel approach to solve the generative planning problem for temporally extended goals for hybrid systems, involving both continuous and discrete actions.

Heuristic Planning for PDDL+ Domains

DiNo is a new planner capable of tackling complex problems with non-linear system dynamics governing the continuous evolution of states based on the discretise-and-validate approach and uses the novel Staged Relaxed Planning Graph+ (SRPG+) heuristic, which is introduced in this paper.

COLIN: Planning with Continuous Linear Numeric Change

In this paper we describe COLIN, a forward-chaining heuristic search planner, capable of reasoning with COntinuous LINear numeric change, in addition to the full temporal semantics of PDDL2.1.
...