Sampling-based tree search with discrete abstractions for motion planning with dynamics and temporal logic

McMahon, James; Plaku, Erion

doi:10.1109/iros.2014.6943085

Cited by 35 publications

(31 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DROMOS is compared with LTLSYCLOP and to a more recent LTL motion planner . Scalability is evaluated by increasing the number of goals and color groups.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Comparison results DROMOS is compared with LTLSYCLOP and to a more recent LTL motion planner , referred to as LTLIROS 14, which was shown to be faster than LTLSYCLOP . These motion planners converted the LTL formula into an automaton using techniques from model checking, and then combined the LTL automaton with the adjacency graph of a workspace triangulation in order to guide the motion‐tree expansion.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…This can be achieved by using the connectives “eventually, and, or” to indicate that the vehicle will eventually visit at least one goal from each group. Motion planning with LTL is part of an increasing body of work that seeks to combine task and motion planning . In particular, LTL motion planners, which combine sampling‐based motion planning with discrete search, can be applied to the problems considered here as they take the vehicle dynamics into account .…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Multi‐group motion planning in virtual environments

Plaku

Rashidian

Edelkamp

2016

Computer Animation & Virtual

Self Cite

View full text Add to dashboard Cite

Toward enhancing automation, this paper proposes an efficient approach for multi-group motion planning, where the set of goals is divided into k groups and the objective is to compute a collision-free and dynamically feasible trajectory that enables a virtual vehicle to reach at least one goal from each group. The approach works with ground and aerial vehicles operating in complex environments containing numerous obstacles. In addition to modeling the vehicle dynamics by differential equations, the approach can use physics-based game engines, which provide an increased level of realism. The approach is based on a hybrid search that uses generalized traveling salesman tours over a probabilistic roadmap to effectively guide the sampling-based expansion of a motion tree. As the motion tree is expanded with collision-free and dynamically feasible trajectories, tours are adjusted based on a partition of the motion tree into equivalence classes. This gives the approach the flexibility to discover new tours that avoid collisions and are compatible with the vehicle dynamics. Comparisons to related work show significant improvements both in terms of runtime and solution length.

show abstract

“…DROMOS is compared with LTLSYCLOP and to a more recent LTL motion planner . Scalability is evaluated by increasing the number of goals and color groups.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Multi‐group motion planning in virtual environments

Plaku

Rashidian

Edelkamp

2016

Computer Animation & Virtual

Self Cite

View full text Add to dashboard Cite

show abstract

“…Several works [21,22,23,24] propose incorporating both the robot dynamics and the given LTL constraints in a continuous space. A continuous state space can be abstracted into a discrete state space and a continuous path is derived by sampling guided by the high-level discrete plan [22,23,24]. Other works have focused on grounding natural language to LTL expressions [9,10,17] to further allow a robot to make use of these LTL specifications.…”

Section: Related Workmentioning

confidence: 99%

Planning with State Abstractions for Non-Markovian Task Specifications

Oh¹,

Patel²,

Nguyen³

et al. 2019

Robotics: Science and Systems XV

View full text Add to dashboard Cite

Often times, we specify tasks for a robot using temporal language that can also span different levels of abstraction. The example command "go to the kitchen before going to the second floor" contains spatial abstraction, given that "floor" consists of individual rooms that can also be referred to in isolation ("kitchen", for example). There is also a temporal ordering of events, defined by the word "before". Previous works have used Linear Temporal Logic (LTL) to interpret temporal language (such as "before"), and Abstract Markov Decision Processes (AMDPs) to interpret hierarchical abstractions (such as "kitchen" and "second floor"), separately. To handle both types of commands at once, we introduce the Abstract Product Markov Decision Process (AP-MDP), a novel approach capable of representing non-Markovian reward functions at different levels of abstractions. The AP-MDP framework translates LTL into its corresponding automata, creates a product Markov Decision Process (MDP) of the LTL specification and the environment MDP, and decomposes the problem into subproblems to enable efficient planning with abstractions. AP-MDP performs faster than a non-hierarchical method of solving LTL problems in over 95% of tasks, and this number only increases as the size of the environment domain increases. We also present a neural sequenceto-sequence model trained to translate language commands into LTL expression, and a new corpus of non-Markovian language commands spanning different levels of abstraction. We test our framework with the collected language commands on a drone, demonstrating that our approach enables a robot to efficiently solve temporal commands at different levels of abstraction.

show abstract

“…Moreover a lazy-search approach was used for the high level planning thus resulting in computational speedups by 10 times for the second order non-linear hybrid controller compared with the previous method. Moreover sampling based Tree-Search motion planning with discrete abstractions for specifications using temporal logic proposed by McMahon et al [8]. In this framework the authors suggested very low cost motion trajectories that satisfy CoSafe LTL.…”

Section: Related Workmentioning

confidence: 99%

Linear Temporal Logic-based Mission Planning

Kumar¹,

Kala²

2016

IJIMAI

View full text Add to dashboard Cite

-In this paper, we describe the Linear Temporal Logic-based reactive motion planning. We address the problem of motion planning for mobile robots, wherein the goal specification of planning is given in complex environments. The desired task specification may consist of complex behaviors of the robot, including specifications for environment constraints, need of task optimality, obstacle avoidance, rescue specifications, surveillance specifications, safety specifications, etc. We use Linear Temporal Logic to give a representation for such complex task specification and constraints. The specifications are used by a verification engine to judge the feasibility and suitability of plans. The planner gives a motion strategy as output. Finally a controller is used to generate the desired trajectory to achieve such a goal. The approach is tested using simulations on the LTLMoP mission planning tool, operating over the Robot Operating System. Simulation results generated using high level planners and low level controllers work simultaneously for mission planning and controlling the physical behavior of the robot.

show abstract

Sampling-based tree search with discrete abstractions for motion planning with dynamics and temporal logic

Cited by 35 publications

References 22 publications

Multi‐group motion planning in virtual environments

Multi‐group motion planning in virtual environments

Planning with State Abstractions for Non-Markovian Task Specifications

Linear Temporal Logic-based Mission Planning

Contact Info

Product

Resources

About