Erion Plaku

Sampling-based roadmap of trees for parallel motion planning

This paper shows how to effectively combine a sampling-based method primarily designed for multiple-query motion planning [probabilistic roadmap method (PRM)] with sampling-based tree methods primarily designed for single-query motion planning (expansive space trees, rapidly exploring random trees, and others) in a novel planning framework that can be efficiently parallelized. Our planner not only achieves a smooth spectrum between multiple-query and single-query planning, but it combines advantages of both. We present experiments which show that our planner is capable of solving problems that cannot be addressed efficiently with PRM or single-query planners. A key advantage of our planner is that it is significantly more decoupled than PRM and sampling-based tree planners. Exploiting this property, we designed and implemented a parallel version of our planner. Our experiments show that our planner distributes well and can easily solve high-dimensional problems that exhaust resources available to single machines and cannot be addressed with existing planners.

Motion Planning With Dynamics by a Synergistic Combination of Layers of Planning

To efficiently solve challenges related to motion-planning problems with dynamics, this paper proposes treating motion planning not just as a search problem in a continuous space but as a search problem in a hybrid space consisting of discrete and continuous components. A multilayered framework is presented which combines discrete search and sampling-based motion planning. This framework is called synergistic combination of layers of planning ( SyCLoP) hereafter. Discrete search uses a workspace decomposition to compute leads, i.e., sequences of regions in the neighborhood that guide sampling-based motion planning during the state-space exploration. In return, information gathered by motion planning, such as progress made, is fed back to the discrete search. This combination allows SyCLoP to identify new directions to lead the exploration toward the goal, making it possible to efficiently find solutions, even when other planners get stuck. Simulation experiments with dynamical models of ground and flying vehicles demonstrate that the combination of discrete search and motion planning in SyCLoP offers significant advantages. In fact, speedups of up to two orders of magnitude were obtained for all the sampling-based motion planners used as the continuous layer of SyCLoP.

Sampling-Based Motion and Symbolic Action Planning with geometric and differential constraints

To compute collision-free and dynamically-feasibile trajectories that satisfy high-level specifications given in a planning-domain definition language, this paper proposes to combine sampling-based motion planning with symbolic action planning. The proposed approach, Sampling-based Motion and Symbolic Action Planner (SMAP), leverages from sampling-based motion planning the underlying idea of searching for a solution trajectory by selectively sampling and exploring the continuous space of collision-free and dynamically-feasible motions. Drawing from AI, SMAP uses symbolic action planning to identify actions and regions of the continuous space that sampling-based motion planning can further explore to significantly advance the search. The planning layers interact with each-other through estimates on the utility of each action, which are computed based on information gathered during the search. Simulation experiments with dynamical models of vehicles carrying out tasks given by high-level STRIPS specifications provide promising initial validation, showing that SMAP efficiently solves challenging problems.

Discrete Search Leading Continuous Exploration for Kinodynamic Motion Planning

This paper presents the Discrete Search Lead- ing continuous eXploration (DSLX) planner, a multi-resolution approach to motion planning that is suitable for challenging problems involving robots with kinodynamic constraints. Initially the method decomposes the workspace to build a graph that encodes the physical adjacency of the decomposed regions. This graph is searched to obtain leads, that is, sequences of regions that can be explored with sampling-based tree methods to generate solution trajectories. Instead of treating the discrete search o f the adjacency graph and the exploration of the continuous state space as separate components, DSLX passes information from one to the other in innovative ways. Each lead suggests what regions to explore and the exploration feeds back information to the discrete search to improve the quality of future leads. Information is encoded in edge weights, which indicate the importance of including the regions associated with an edge in the next exploration step. Computation of weights, leads, and the actual exploration make the core loop of the algorithm. Extensive experimentation shows that DSLX is very versatile. The discrete search can drastically change the lead to reflect new information allowing DSLX to find solutions even when sampling-based tree planners get stuck. Experimental results on a variety of challenging kinodynamic motion planning problems show computational speedups of two orders of magnitude over other widely used motion planning methods.

Probabilistic Roadmaps of Trees for Parallel Computation of Multiple Query Roadmaps

We propose the combination of techniques that solve multiple queries for motion planning problems with single query planners in a motion planning framework that can be efficiently parallelized. In multiple query motion planning, a data structure is built during a preprocessing phase in order to quickly respond to on-line queries. Alternatively, in single query planning, there is no preprocessing phase and all computations occur during query resolution. This paper shows how to effectively combine a powerful sample-based method primarily designed for multiple query planning (the Probabilistic Roadmap Method - PRM) with sample-based tree methods that were primarily designed for single query planning (such as Expansive Space Trees, Rapidly Exploring Random Trees, and others). Our planner, which we call the Probabilistic Roadmap of Trees (PRT), uses a tree algorithm as a subroutine for PRM. The nodes of the PRM roadmap are now trees. We take advantage of the very powerful sampling schemes of recent tree planners to populate our roadmaps. The combined sampling scheme is in the spirit of the non-uniform sampling and refinement techniques employed in earlier work on PRM. PRT not only achieves a smooth spectrum between multiple query and single query planning but it combines advantages of both. We present experiments which show that PRT is capable of solving problems that cannot be addressed efficiently with PRM or single-query planners. A key advantage of PRT is that it is significantly more decoupled than PRM and sample-based tree planners. Using this property, we designed and implemented a parallel version of PRT. Our experiments show that PRT distributes well and can easily solve high dimensional problems that exhaust resources available to single machines.

OOPS for Motion Planning: An Online, Open-source, Programming System

The success of sampling-based motion planners has resulted in a plethora of methods for improving planning components, such as sampling and connection strategies, local planners and collision checking primitives. Although this rapid progress indicates the importance of the motion planning problem and the maturity of the field, it also makes the evaluation of new methods time consuming. We propose that a systems approach is needed for the development and the experimental validation of new motion planners and/or components in existing motion planners. In this paper, we present the online, open-source, programming system for motion planning (OOPSMP), a programming infrastructure that provides implementations of various existing algorithms in a modular, object-oriented fashion that is easily extendible. The system is open-source, since a community-based effort better facilitates the development of a common infrastructure and is less prone to errors. We hope that researchers will contribute their optimized implementations of their methods and thus improve the quality of the code available for use. A dynamic Web interface and a dynamic linking architecture at the programming level allows users to easily add new planning components, algorithms, benchmarks, and experiment with different parameters. The system allows the direct comparison of new contributions with existing approaches on the same hardware and programming infrastructure

Falsification of LTL safety properties in hybrid systems

This paper develops a novel approach for the falsification of safety properties given by a syntactically safe linear temporal logic (LTL) formula

Falsification of LTL Safety Properties in Hybrid Systems

{\phi}