Temporal Planning Research Articles

A digital twin-based traffic light management system using BIRCH algorithm

Urban transportation networks are vital for the economic and environmental well-being of cities and they are faced with the integration of Human-Driven Vehicles (HVs) and Connected and Autonomous Vehicles (CAVs) challenge. Most of the traditional traffic management systems fail to effectively manage the dynamic and complex flows of mixed traffic, mainly because of large computational requirements and the restrictions that control models of traffic lights directly based on extensive and continuous training data. Most of the times, the operational flexibility of CAVs is severely compromised for the safety of HVs, or CAVs are given high priority without taking into account the efficiency of HVs leading to lower performance, especially at low CAV penetration rates. On the other hand, the existing adaptive traffic light approaches were usually partial and could not adapt to the real-time behaviors of the traffic system. Some systems operate with inflexible temporal control plans that cannot react to variations in traffic flow or use adaptive control strategies that are based on a limited set of static traffic conditions. This paper presents a novel traffic light control approach utilizing the BIRCH (Balanced Iterative Reducing and Clustering using Hierarchies) clustering algorithm combined with digital twins for a more adaptive and efficient system. The BIRCH is effective in processing large datasets because it clusters data points incrementally and dynamically into a small set of representatives. The suggested method does not only enable better simulation and prediction of traffic patterns but also makes possible the real-time adaptive control of traffic signals at signalized intersections. It also improves traffic flow, reduces congestion, and minimizes vehicle idling time by adjusting the green and red light durations dynamically based on both real-time and historical traffic data. This approach is assessed under different traffic intensities, which include low, moderate, and high, while efficiency, fuel consumption, and the number of stops are being compared with the traditional and the existing adaptive traffic management systems.

Fast Temporal Logic Mission Planning of Multiple Robots: A Planning Decision Tree Approach

Fast Temporal Logic Mission Planning of Multiple Robots: A Planning Decision Tree Approach

Multi-Agent Temporal Task Solving and Plan Optimization

Multi-Agent Temporal Task Solving and Plan Optimization

Exploring self-experience practices in dementia care: A scoping review.

Recognised as essential for high-quality dementia service, person-centred care aims to understand and respect the unique needs of each individual. Self-experience practices may offer caregivers an opportunity to acquire knowledge, empathy, and skills related to person-centred care, especially through recreating experiences similar to dementia. Given the need to enhance the understanding of self-experience practices in dementia care, a more comprehensive investigation of these training interventions for (future) caregivers is needed. We conducted a scoping review to map the evidence on the use of self-experience practices in dementia training. We systematically searched Cochrane Library, MEDLINE via PubMed, CINAHL, and Web of Science. We also searched for grey literature, as well as registry entries, and conducted backward citation tracking of included reviews. We analysed data on intervention characteristics, factors influencing the implementation, and learning outcomes based on Kirkpatrick's model. We included 44 reports across 30 intervention programmes. The majority of reports (91%) were published from 2016 onwards, with 32% originating from the USA and 25% from the UK. We identified passive, interactive, immersive, and multicomponent self-experience interventions in dementia education and training. Learning outcomes based on Kirkpatrick's model were fairly distributed across all identified modalities. Both consumers and providers emphasised aspects related to the development and implementation of practices, particularly organisational-related considerations such as temporal and spatial planning of trainings. Our review highlights diverse interventions incorporating self-experience practices, with an increasing role for technological tools. While self-experience interventions engage participants, the impact on individuals with dementia and organisational levels remain largely unreported. Our overview, informed by current literature, underscores unique considerations and challenges associated with dementia-related self-experience practices. Implementing and evaluating complex training interventions using self-experience practices should consider ethical aspects. Registry: Registered within the Open Science Framework (available at https://osf.io/fycxa/).

Interactive Theorem Provers: Applications in AI, Opportunities, and Challenges

Interactive theorem provers (ITPs) are computer programs in which axioms and a conjecture are stated in a formal language, and a user provides the ITP with relatively high-level steps of a formal proof for the conjecture. Then, by invoking automated theorem provers, the ITP tries to generate low-level steps that fill the gaps between the steps provided by the user, thus forming a complete formal proof of the conjecture. The ITP also checks the entire formal proof against the axioms, thus confirming the soundness of all derivations in the formal proof. In this talk, I will discuss the existing opportunities and potential benefits to applying ITPs to reason about and verify AI concepts, algorithms, and software. I will also discuss the challenges we have to being able to apply ITPs in AI and reap those benefits. I will do so by discussing a number of my previous projects on the application of ITPs to different AI concepts, algorithms, and software systems. These projects span different areas of planning (classical planning, temporal planning, and planning under uncertainty) as well as algorithms with applications in algorithmic game theory, like general graph matching and online matching.

Bidirectional Temporal Plan Graph: Enabling Switchable Passing Orders for More Efficient Multi-Agent Path Finding Plan Execution

The Multi-Agent Path Finding (MAPF) problem involves planning collision-free paths for multiple agents in a shared environment. The majority of MAPF solvers rely on the assumption that an agent can arrive at a specific location at a specific timestep. However, real-world execution uncertainties can cause agents to deviate from this assumption, leading to collisions and deadlocks. Prior research solves this problem by having agents follow a Temporal Plan Graph (TPG), enforcing a consistent passing order at every location as defined in the MAPF plan. However, we show that TPGs are overly strict because, in some circumstances, satisfying the passing order requires agents to wait unnecessarily, leading to longer execution time. To overcome this issue, we introduce a new graphical representation called a Bidirectional Temporal Plan Graph (BTPG), which allows switching passing orders during execution to avoid unnecessary waiting time. We design two anytime algorithms for constructing a BTPG: BTPG-naïve and BTPG-optimized. Experimental results show that following BTPGs consistently outperforms following TPGs, reducing unnecessary waits by 8-20%.

Abstract Action Scheduling for Optimal Temporal Planning via OMT

Given the model of a system with explicit temporal constraints, optimal temporal planning is the problem of finding a schedule of actions that achieves a certain goal while optimizing an objective function. Recent approaches for optimal planning reduce the problem to a series of queries to an Optimization Modulo Theory (OMT) solver: each query encodes a bounded version of the problem, with additional abstract actions representing an over-approximation of the plans beyond the bound. This technique suffers from performance issues, mainly due to the looseness of the over-approximation, which can include many non-executable plans. In this paper, we propose a refined abstraction for solving optimal temporal planning via OMT by introducing abstract scheduling constraints, which have a double purpose. First, they enforce a partial ordering of abstract actions based on mutual dependencies between them, which leads to a better makespan estimation and allows to prove optimality sooner. Second, they implicitly forbid circular self-enabling of abstract actions, which is a common cause of spurious models that severely affects performance in existing approaches. We prove the soundness and completeness of the resulting approach and empirically demonstrate its superiority with respect to the state of the art.

A Comparative Analysis of Generative Artificial Intelligence Tools for Natural Language Processing

Generative artificial intelligence tools have recently attracted a great deal of attention. This is because of their huge advantages, which include ease of usage, quick generation of answers to requests, and the human-like intelligence they possess. This paper presents a vivid comparative analysis of the top 9 generative artificial intelligence (AI) tools, namely ChatGPT, Perplexity AI, YouChat, ChatSonic, Google's Bard, Microsoft Bing Assistant, HuggingChat, Jasper AI, and Quora's Poe, paying attention to the Pros and Cons each of the AI tools presents. This comparative analysis shows that the generative AI tools have several Pros that outweigh the Cons. Further, we explore the transformative impact of generative AI in Natural Language Processing (NLP), focusing on its integration with search engines, privacy concerns, and ethical implications. A comparative analysis categorizes generative AI tools based on popularity and evaluates challenges in development, including data limitations and computational costs. The study highlights ethical considerations such as technology misuse and regulatory challenges. Additionally, we delved into AI Planning techniques in NLP, covering classical planning, probabilistic planning, hierarchical planning, temporal planning, knowledge-driven planning, and neural planning models. These planning approaches are vital in achieving specific goals in NLP tasks. In conclusion, we provide a concise overview of the current state of generative AI, including its challenges, ethical considerations, and potential applications, contributing to the academic discourse on human-computer interaction.

Importance of geotechnical soil properties for precision Forest activities in a karst area

Some soil behaviors change significantly as water content varies over time. The particle size distribution of soils has a direct impact on mechanical properties such as soil water content, resistance to dispersion, swelling-shrinkage, fluidity, plasticity, and stickiness. This study was conducted to investigate the usability of Atterberg limits, consistency index and coefficient of linear extensibility (COLE) in the temporal planning of ecosystem restoration activities such as silvicultural interventions, tillage, afforestation, and the construction of forest roads, etc. Surface soil samples were collected from the sections numbered 263, 264, 266, 268, 317, 318, 319, 323, 324,325 and 366 of the degraded forest of the Andırın forestry operations department. The COLE, liquid limit (LL), plastic limit (PL), plasticity index and consistency index values of soil samples were determined. The LL values ranged from 17.5 to 62.4%, the PL values from 8.2 to 46.8% and the PI values from 6.4 to 15.5. The highest COLE value (0.13) was recorded in the section 318, while the lowest COLE value (0.03) was in section 325.The LL and PL values have a positive linear relationship with clay and organic matter content. All sections have karstic characteristics, but the mechanical characteristics of the soils differ significantly between the sections. Silvicultural interventions carried out especially in section 318, which had the lowest consistency index (Ic = 0.70), and sections 263, 264, 317 and 319, where the consistency index is >2,should take mechanical properties into account, and the planting time intervals should be determined, accordingly for sustainable forestry.

Local Observation Based Reactive Temporal Logic Planning of Human-Robot Systems

Local Observation Based Reactive Temporal Logic Planning of Human-Robot Systems

ВРЕМЕННОЙ ПЛАН УСТНОГО НАРРАТИВА КАК ПРОЕКЦИЯ СУБЪЕКТА ПОВЕСТВОВАНИЯ

The article discusses the features of modeling the category of time in oral narratives with reliability. The most essential property of the time of such narratives is the orientation to the actual moment of speech: the narrative about the events of the past is built taking into account the time plan of the situation of the conversation. This is reflected by means of different language levels – aspectual-temporal forms of verbs, features of the reference of actors, forms of direct and indirect speech, vocabulary with temporal semantics. Their analysis in the article is based on the material of autobiographical memorates. The reflection of three time points at once is considered: the moment of speech, the moment of the narrator’s first perception of the story from a participant in the events, and the moment of the events described in the text. A comparison of these features with the traditional narrative genres of folklore shows that the main difference in the organization of the temporal plan lies in the nature of the relationship between text time and the moment of speech. This is due to the different position of the speaker in relation to the chronotope of the text. Thus, the time plan of oral narration is a projection of the narrating subject

Techno-economic analysis for design and management of international green hydrogen supply chain under uncertainty: An integrated temporal planning approach

The international green hydrogen supply chain (HSC) is anticipated to play a pivotal role in the ongoing energy transition. Our research endeavors to assess the implications of considering fast timescale volatility in renewable energy sources and uncertainties in demand on the design and evaluation of the international green hydrogen supply chain. To achieve this objective, we introduce a comprehensive bi-level optimization method for evaluating the economic viability of the HSC between nations. In the upper level of the optimization, capacity investments are determined using Bayesian optimization and Hyperband (BOHB) for multiple components, including turbines, PV panels, batteries, water electrolyzers, hydrogen liquefaction plants, hydrogen tanks, and liquid hydrogen (LH2) ships. The lower level focuses on the optimal scheduling of LH2 shipments and the operation of each facility, utilizing a mixed-integer linear programming (MILP) model that considers lead time and uncertainties in both supply and demand. We conduct case studies involving nine projects, encompassing three potential import and export countries, to demonstrate and analyze the effectiveness of the proposed framework. Furthermore, we delve into the impacts of various factors, such as economies of scale, lead time, and the minimum operating constraint of the electrolyzer, on the economic performance of the green HSC project. The study also explores the optimal balance between facility installation scales and their relationships with techno-economic parameters, providing valuable insights for future research, technological advancement and supply chain design.

STP4: spatio temporal path planning based on pedestrian trajectory prediction in dense crowds

This article proposes a means of autonomous mobile robot navigation in dense crowds based on predicting pedestrians’ future trajectories. The method includes a pedestrian trajectory prediction for a running mobile robot and spatiotemporal path planning for when the path crosses with pedestrians. The predicted trajectories are converted into a time series of cost maps, and the robot achieves smooth navigation without dodging to the right or left in crowds; the path planner does not require a long-term prediction. The results of an evaluation implementing this method in a real robot in a science museum show that the trajectory prediction works. Moreover, the proposed planning’s arrival times is 26.4% faster than conventional 2D path planning’s arrival time in a simulation of navigation in a crowd of 50 people.

AI temporal planning for energy smart buildings

Buildings are responsible for about one-third of industrialised countries’ overall energy consumption and greenhouse gas emissions. As if this was not enough, recently, energy prices significantly increased and affected all economic areas. Making buildings more efficient and effective is the step needed toward cost reductions. Key enablers of cost-effectiveness are leveraging batteries, awareness of and adaptability to energy prices, and integrating powerful reasoning techniques to optimally and flexibly operate buildings. Researchers have tackled many of these aspects using a variety of approaches. Whereas a less investigated one is that of AI planning to coordinate actions and save energy in buildings. However, generating plans based on signals of energy prices and leveraging batteries is still an open research problem. To address this high-potential aspect, we engineer an AI planning system for improving the energy-cost effectiveness in buildings by coordinating the building’s operation based on day-ahead prices and the use of a battery, all without sacrificing the comfort of building occupants. We propose to exploit temporal planning due to its powerful modelling and reasoning features, especially in explicitly addressing time. We evaluate the effectiveness of the system in several scenarios with varying building environmental conditions. We compare the energy cost from using our planning system to a baseline cost, where we record a reduction of 43rage in favour of our system.

Spatiotemporal variations in the acoustic presence of dugongs and vessel traffic around Talibong Island, Thailand: Inputs for local coastal management from passive acoustical aspects

Examining the spatiotemporal habitat use by marine megafauna and human activities at a fine scale is important to achieve harmonised management of coastal areas. Passive acoustic monitoring (PAM) can provide this information by observing animal vocalisations and the sounds generated by motorised vessels. Dugongs (Dugong dugon), which are endangered herbivorous mammals inhabiting coastal seas, communicate through social calls. Although their spatiotemporal acoustic presence on a fine scale could assist in prioritizing local marine spatial planning, such knowledge is limited. To address this gap, we examined the spatiotemporal pattern of the acoustic presence of dugongs and its correlation with environmental and anthropological factors; additionally, the overlap of these areas with vessel traffic was illustrated. Underwater recorders were deployed at 11 locations around Talibong Island, Thailand, for one month in both rainy and dry seasons. Based on the recorded sound stream, dugong calls and vessel sounds were automatically detected using custom-made software, and false detections were removed by manual examinations. In 2019 and 2020, 1933 h and 2719 h of recordings, respectively, revealed that while dugongs had a clear spatial preference for vocal communication at some locations, their temporal patterns varied among locations. Further, their acoustic presence was significantly correlated with environmental and anthropological factors at some locations, while these factors varied among other locations. However, the distribution of vessel traffic was spatially and temporally stable. These results suggested that (1) spatial management of vocalisation areas can effectively conserve dugongs by protecting their social behaviour and (2) temporal planning may reduce the potential disturbance risk to dugongs. Moreover, to achieve harmonised marine spatial planning in coastal areas, the PAM approach for social calls can be effectively employed to provide a unique layer of habitat use for vocalising species and vessel traffic on a fine scale.

Quantifying the cumulative cooling effects of 3D building and tree shade with high resolution thermal imagery in a hot arid urban climate

Shading is an effective heat-mitigation strategy, with tree and building shade naturally cooling heated surfaces in hot-arid climates. However, increasing shade through tree planting and building arrangement has associated costs, such as tree maintenance and loss of solar access. To make strategic decisions, quantifying shade’s cooling effectiveness is crucial. This study examines the extent to which shade reduces land surface temperature (LST) in a hot-arid residential environment by considering shade’s areal coverage, overall duration, and time of day. Using fine-resolution 3D city models (1 m/pixel), land cover classification (1 m/pixel), and high-resolution thermal imagery (6 m/pixel) for Tempe, Arizona, USA, hourly shade calculations are conducted from 7:30 to 13:30 on July 12, 2011. The relationships among the observed LST at 13:30, land cover types, and shade characteristics are analyzed using linear and spatial regressions. The results reveal that shade’s cooling effect is cumulative, rather than instantaneous, as surface cooling by earlier shade persists to later times to some degree. Areas shaded for longer hours are cooler than those shaded only temporarily. The results further indicate that tree-shaded areas are significantly cooler than those shaded by other features, including buildings, with the difference increasing with shade duration. Shifting a 6 × 6 m area from 0% to 100% shade in the early morning generates a 2.3℃ LST reduction at 13:30. The same shift in shade for the whole morning and the entire period (7:30–13:30) would lower LST by 8.3℃ and 11.3℃, respectively. The importance of temporal shade planning and policy recommendation for urban heat mitigation is discussed.

Dynamic Controllability of Temporal Plans in Uncertain and Partially Observable Environments

The formalism of Simple Temporal Networks (STNs) provides methods for evaluating the feasibility of temporal plans. The basic formalism deals with the consistency of quantitative temporal requirements on scheduled events. This implicitly assumes a single agent has full control over the timing of events. The extension of Simple Temporal Networks with Uncertainty (STNU) introduces uncertainty into the timing of some events. Two main approaches to the feasibility of STNUs involve (1) where a single schedule works irrespective of the duration outcomes, called Strong Controllability, and (2) whether a strategy exists to schedule future events based on the outcomes of past events, called Dynamic Controllability. Case (1) essentially assumes the timing of uncertain events cannot be observed by the agent while case (2) assumes full observability. The formalism of Partially Observable Simple Temporal Networks with Uncertainty (POSTNU) provides an intermediate stance between these two extremes, where a known subset of the uncertain events can be observed when they occur. A sound and complete polynomial algorithm to determining the Dynamic Controllability of POSTNUs has not previously been known; we present one in this paper. This answers an open problem that has been posed in the literature. The approach we take factors the problem into Strong Controllability micro-problems in an overall Dynamic Controllability macro-problem framework. It generalizes the notion of labeled distance graph from STNUs. The generalized labels are expressed as max/min expressions involving the observables. The paper introduces sound generalized reduction rules that act on the generalized labels. These incorporate tightenings based on observability that preserve dynamic viable strategies. It is shown that if the generalized reduction rules reach quiescence without exposing an inconsistency, then the POSTNU is Dynamically Controllable (DC). The paper also presents algorithms that apply the reduction rules in an organized way and reach quiescence in a polynomial number of steps if the POSTNU is Dynamically Controllable. Remarkably, the generalized perspective leads to a simpler and more uniform framework that applies also to the STNU special case. It helps illuminate the previous methods inasmuch as the max/min label representation is more semantically clear than the ad-hoc upper/lower case labels previously used.

Large-scale agent-based simulation model of pedestrian traffic flows

Mobility patterns of pedestrians at a very high spatial and temporal resolution support urban planning strategies and facilitate a better understanding of the transport system. In this study, we develop an agent-based model that simulates disaggregated pedestrian traffic flows at a regional scale. This model is designed to overcome limitations of existing approaches in pedestrian traffic modelling by incorporating several decision processes that are defined by probabilistic rules. These rules include activity type, mode, and route choices. The results of a case study in Salzburg (Austria) show traffic flows concentrated in the city centre and along the river. Performed complexity analysis justifies the structure and logic of the modelled system by showing improvements in results during the stepwise implementation of model concepts. We also performed uncertainty analysis to provide information on the accuracy of the modelled results, showing strong and moderate correlations against observational data.

A Fast Rescheduling Algorithm for Real-Time Multi-Robot Coordination [Extended Abstract

One area of research in Multi-Agent Path Finding (MAPF) is to determine how re-planning can be efficiently achieved in the case of the delay of an agent. One option is to determine a new wait ordering to find the most optimal new solution that can be produced by re-ordering the wait order. We propose to use an Edge-Switchable Temporal Plan Graph and an augmented A* algorithm, called Switchable-Edge Search, to approach finding a new optimal wait order. While this is a work in progress still, we have discovered several optimizations for this algorithm, and the results show promising increases in efficiency for the algorithm. We have analyzed our present efficiency in a variety of conditions by measuring re-planning speed in different maps, with varying numbers of agents and randomized scenarios for agents' start and goal locations. We hope that, as we proceed with optimization, we can show that such an approach can be more efficient in practice and be used instead of re-running MAPF to perform cheap re-planning in such situations.

A faster algorithm for converting simple temporal networks with uncertainty into dispatchable form

A Simple Temporal Network with Uncertainty (STNU) is a data structure for reasoning about time constraints on actions that may have uncertain durations. An STNU is dispatchable if it can be executed in real-time with minimal computation 1) satisfying all constraints no matter how the uncertain durations play out and 2) retaining maximum flexibility. The fastest known algorithm for converting STNUs into dispatchable form runs in O(n3) time, where n is the number of timepoints. This paper presents a faster algorithm that runs in O(mn+kn2+n2log⁡n) time, where m is the number of edges and k is the number of uncertain durations. This performance is particularly meaningful in fields like Business Process Management, where sparse STNUs can represent temporal processes or plans. For sparse STNUs, our algorithm generates dispatchable forms in time O(n2log⁡n), a significant improvement over the O(n3)-time previous fastest algorithm.