A Distributed Framework for Multi-Robot Task Planning with Temporal Logic Specifications

Manipulation planning from high-level task specifications, even though highly desirable, is a challenging problem. The large dimensionality of manipulators and complexity of task specifications make the problem computationally intractable. This work introduces a manipulation planning framework with linear temporal logic (LTL) specifications. The use of LTL as the specification language allows the expression of rich and complex manipulation tasks. The framework deals with the state-explosion problem through a novel abstraction technique. Given a robotic system, a workspace consisting of obstacles, manipulable objects, and locations of interest, and a co-safe LTL specification over the objects and locations, the framework computes a motion plan to achieve the task through a synergistic multi-layered planning architecture. The power of the framework is demonstrated through case studies, in which the planner efficiently computes plans for complex tasks. The case studies also illustrate the ability of the framework in intelligently moving away objects that block desired executions without requiring backtracking.

This paper considers robot motion planning under temporal logic constraints in probabilistic maps obtained by semantic simultaneous localization and mapping (SLAM). The uncertainty in a map distribution presents a great challenge for obtaining correctness guarantees with respect to the linear temporal logic (LTL) specification. We show that the problem can be formulated as an optimal control problem in which both the semantic map and the logic formula evaluation are stochastic. Our first contribution is to reduce the stochastic control problem for a subclass of LTL to a deterministic shortest path problem by introducing a confidence parameter $delta$. A robot trajectory obtained from the deterministic problem is guaranteed to have minimum cost and to satisfy the logic specification in the true environment with probability $delta$. Our second contribution is to design an admissible heuristic function that guides the planning in the deterministic problem towards satisfying the temporal logic specification. This allows us to obtain an optimal and very efficient solution using the A* algorithm. The performance and correctness of our approach are demonstrated in a simulated semantic environment using a differential-drive robot.

We present a method to find an optimal policy with respect to a reward function for a discounted Markov decision process under general linear temporal logic (LTL) specifications. Previous work has either focused on maximizing a cumulative reward objective under finite-duration tasks or maximizing an average reward for persistent (e.g., surveillance) tasks. This paper extends and generalizes these results by introducing a pair of occupancy measures to express the LTL satisfaction objective and the expected discounted reward objective, respectively. These occupancy measures are then connected to a single policy via a novel reduction resulting in a mixed integer linear program whose solution provides an optimal policy. Our formulation can also be extended to include additional constraints with respect to secondary reward functions. We illustrate the effectiveness of our approach in the context of robotic motion planning for complex missions under uncertainty and performance objectives.

In this paper, we investigate the design of multirobot warehouse automation systems with complex high-level tasks. We consider a warehouse environment where a group of AGVs move in a grid-partitioned workspace to deliver goods upon requests automatically. The design objective is to synthesize a high-level controller/planner that coordinates the multi-robot system to fulfill the entire task. We use linear temporal logic (LTL) formulas to describe the desired task specifications. Then the controller is generated automatically based on the LTL formula using the theory of reactive synthesis. Compared with most of the existing planning algorithms for warehouse systems, the proposed method is formal in the sense that: (i) the controller is correct-by-construction with provably satisfication guarantees; (ii) it can handle complex temporal tasks in a user-friendly manner; (iii) our framework can also handle the situation of multiple robots with multiple requests. Finally, we implement the proposed synthesis procedure and illustrate our results for multi-robot systems by simulations.

This paper proposes a novel version of the vehicle routing problem (VRP). Instead of servicing all the customers, feasible solutions of the VRP instance are forced to satisfy a set of complex high-level tasks given as a metric temporal logic (MTL) specification, which allows complex quantitative timing constraints to be incorporated into the problem. For the resulting vehicle routing problem with metric temporal logic specifications (VRPMTL), a mixed-integer linear programming (MILP) based algorithm is provided that solves the problem to optimality. Examples for optimal multi-UAV mission planning are provided where MTL is used as a high level language to specify complex mission tasks.

This letter proposes a learning-based bounded synthesis for a semi-Markov decision process (SMDP) with a linear temporal logic (LTL) specification. In the product of the SMDP and the deterministic <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -co-Büchi automaton ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{d}K$ </tex-math></inline-formula> cBA) converted from the LTL specification, we learn both the winning region of satisfying the LTL specification and the dynamics therein based on reinforcement learning and Bayesian inference. Then, we synthesize an optimal policy satisfying the following two conditions. (1) It maximizes the probability of reaching the wining region. (2) It minimizes a long-term risk for the dwell time within the winning region. The minimization of the long-term risk is done based on the estimated dynamics and a value iteration. We show that, if the discount factor is sufficiently close to one, the synthesized policy converges to the optimal policy as the number of the data obtained by the exploration goes to the infinity.

Dynamic Bayesian networks (DBNs) are compact graphical representations used to model probabilistic systems where interdependent random variables and their distributions evolve over time. In this paper, we study the verification of the evolution of conditional-independence (CI) propositions against temporal logic specifications. To this end, we consider two specification formalisms over CI propositions: linear temporal logic (LTL), and non-deterministic Büchi automata (NBAs). This problem has two variants. Stochastic CI properties take the given concrete probability distributions into account, while structural CI properties are viewed purely in terms of the graphical structure of the DBN. We show that deciding whether a stochastic CI proposition eventually holds is at least as hard as the Skolem problem for linear recurrence sequences, which is a long-standing open problem in number theory. On the other hand, we show that verifying the evolution of structural CI propositions against LTL and NBA specifications is in PSPACE, and is hard for both NP and coNP. We also identify natural restrictions on the graphical structure of the DBN that make the verification of structural CI properties tractable.

In control theory, models of physical processes, such as systems of differential equations, are usually checked against specifications, such as stability and set invariance. In formal methods, rich specifications, such as languages and formulae of temporal logics, are checked against models of software programs and digital circuits, such as finite transition graphs. With the development and integration of cyber physical and safety critical systems, there is an increasing need for computational tools for verification and control of complex systems from rich, temporal logic specifications. The formal verification and synthesis problems have been shown to be undecidable even for very simple classes of infinitespace continuous and hybrid systems. However, provably correct but conservative approaches, in which the satisfaction of a property by a dynamical system is implied by the satisfaction of the property by a finite over-approximation (abstraction) of the system, have received a lot of attention in recent years. Some classes of systems allowing for computationally efficient verification and control from temporal logic specifications are reviewed. For continuous and discrete-time linear systems and continuous-time multi-linear systems, it is shown that finite abstractions can be constructed through polyhedral operations only. By using techniques from model checking and automata games, this allows for verification and control from specifications given as Linear Temporal Logic (LTL) formulae over linear predicates in the state variables. A connection between the existence of Lyapunov functions and finite bisimulations is established for discrete-time linear and switched linear systems. Finally, optimality and correctness requirements are combined in a model predictive approach to generate control strategies for discrete-time linear systems. The usefulness of these computational tools is illustrated with various examples such as verification and synthesis of biological circuits in synthetic biology and motion planning and control in robotics.

A formal approach for run-time verification of web applications using scope-extended LTL

In this paper we propose a methodology for automatically synthesizing motion task controllers based on linear temporal logic (LTL) specifications. The proposed design of the underlying multi-agent controllers possesses a special structure that allows for implicit satisfaction of basic liveness and safety specifications. The resulting closed loop system is of hybrid nature combining the continuous dynamics of the underlying system with the automatically synthesized switching logic that enforces the LTL specification. The effectiveness of the proposed scheme is verified through non-trivial computer simulations.

For human-robot teams that operate in space, safety and robustness are paramount. In situations such as habitat construction, station inspection, or cooperative exploration, incorrect assumptions about the environment or task across the team could lead to mission failure. Thus it is important to resolve any ambiguity about the mission between teammates before embarking on a commanded task. The safeguards guaranteed by formal methods can be used to synthesize correct-by-construction reactive controllers for a robot using Linear Temporal Logic. If a robot fails to synthesize a controller given an instruction, it is clear that there exists a logical inconsistency in the environmental assumptions and/or described interactions. These specifications however are typically crafted in a language unique to the verification framework, requiring the human collaborator to be fluent in the software tool used to construct it. Furthermore, if the controller fails to synthesize, it may prove difficult to easily repair the specification. Language is a natural medium to generate these specifications using modern symbol grounding techniques. Using language empowers non-expert humans to describe tasks to robot teammates while retaining the benefits of formal verification. Additionally, dialogue could be used to inform robots about the environment and/or resolve any ambiguities before mission execution. This paper introduces an architecture for natural language interaction using a symbolic representation that informs the construction of a specification in Linear Temporal Logic. The novel aspect of this approach is that it provides a mechanism for resolving synthesis failure by hypothesizing corrections to the specification that are verified through human-robot dialogue. Experiments involving the proposed architecture are demonstrated using a simulation of an Astrobee robot navigating in the International Space Station.

The fundamental idea of this work is to synthesize reactive controllers such that closed-loop execution trajectories of the system satisfies desired specifications that ensure correct system behaviors, while optimizing a desired performance criteria. We define the correctness of a system's behavior according to the system's relation to the environment, for example, the output trajectories of the system terminate in a goal set without entering an unsafe set. Using Metric Temporal Logic (MTL) specifications we can capture complex system behaviors and timing requirements, such as the output trajectories must pass through a number of way-points within a certain time frame before terminating in the goal set. Given a Mixed Logical Dynamical (MLD) system and system specifications in terms of MTL formula or simpler reach-avoid specifications, our goal is to find a closed-loop trajectory that satisfies the specifications, in non-deterministic environments. Using an MILP framework we search over the space of input signals to obtain such valid trajectories of the system, by adding constraints to satisfy the MTL formula only when necessary, to avoid the exponential complexity of solving MILP problems. We also present experimental results for planning a path in real-time for a mobile robot through a dynamically changing environment with a desired task specification.

We present an energy storage controller synthesis method for power systems with respect to metric temporal logic (MTL) specifications. The power systems with both constant impedance loads and constant power loads are modeled as a set of differential–algebraic equations. After a fault is cleared, with uncertainties in the fault clearing time, the generator machine angles and rotor speed deviations will enter a set of postfault initial states. We use the robust neighborhood approach to cover this set using the initial robust neighborhoods of finitely many simulated postfault trajectories. These simulated postfault trajectories meet the frequency regulation requirements specified in MTL as they are driven by the optimal control input signals obtained through a functional gradient descent approach. In this way, all the possible postfault trajectories with the given uncertainties in the fault clearing time are guaranteed to satisfy the MTL specification. Furthermore, we learn a piecewise linear control law from the data of the simulated trajectories to generate a feedback controller.

We develop a sampling-based motion planning algorithm that combines long-term temporal logic goals with short-term reactive requirements. The mission specification has two parts: (1) a global specification given as a linear temporal logic (LTL) formula over a set of static service requests that occur at the regions of a known environment, and (2) a local specification that requires servicing a set of dynamic requests that can be sensed locally during the execution. The proposed computational framework consists of two main ingredients: (a) an off-line sampling-based algorithm for the construction of a global transition system that contains a path satisfying the LTL formula; and (b) an on-line sampling-based algorithm to generate paths that service the local requests, while making sure that the satisfaction of the global specification is not affected. The off-line algorithm has four main features. First, it is incremental, in the sense that the procedure for finding a satisfying path at each iteration scales only with the number of new samples generated at that iteration. Second, the underlying graph is sparse, which implies low complexity for the overall method. Third, it is probabilistically complete. Fourth, under some mild assumptions, it has the best possible complexity bound. The on-line algorithm leverages ideas from LTL monitoring and potential functions to ensure progress towards the satisfaction of the global specification while servicing locally sensed requests. Examples and experimental trials illustrating the usefulness and the performance of the framework are included.

In this paper, we study the problem of learning to satisfy temporal logic specifications with a group of agents in an unknown environment, which may exhibit probabilistic behaviour. From a learning perspective these specifications provide a rich formal language with which to capture tasks or objectives, while from a logic and automated verification perspective the introduction of learning capabilities allows for practical applications in large, stochastic, unknown environments. The existing work in this area is, however, limited. Of the frameworks that consider full linear temporal logic or have correctness guarantees, all methods thus far consider only the case of a single temporal logic specification and a single agent. In order to overcome this limitation, we develop the first multi-agent reinforcement learning technique for temporal logic specifications, which is also novel in its ability to handle multiple specifications. We provide correctness and convergence guarantees for our main algorithm – ALMANAC (Automaton/Logic Multi-Agent Natural Actor-Critic) – even when using function approximation. Alongside our theoretical results, we further demonstrate the applicability of our technique via a set of preliminary experiments.