This paper challenges a prevailing epistemological assumption in End-to-End Autonomous Driving: that high-performance planning necessitates high-fidelity world reconstruction. Inspired by cognitive science, we propose the Mental Bayesian Causal World Model (MBCWM) and instantiate it as the Tokenized Intent World Model (TIWM), a novel cognitive computing architecture. Its core philosophy posits that intelligence emerges not from pixel-level objective fidelity, but from the Cognitive Consistency between the agent's internal intentional world and physical reality. By synthesizing von Uexküll's $\textit{Umwelt}$ theory, the neural assembly hypothesis, and the triple causal model (integrating symbolic deduction, probabilistic induction, and force dynamics) into an end-to-end embodied planning system, we demonstrate the feasibility of this paradigm on the nuPlan benchmark. Experimental results in open-loop validation confirm that our Belief-Intent Co-Evolution mechanism effectively enhances planning performance. Crucially, in closed-loop simulations, the system exhibits emergent human-like cognitive behaviors, including map affordance understanding, free exploration, and self-recovery strategies. We identify Cognitive Consistency as the core learning mechanism: during long-term training, belief (state understanding) and intent (future prediction) spontaneously form a self-organizing equilibrium through implicit computational replay, achieving semantic alignment between internal representations and physical world affordances. TIWM offers a neuro-symbolic, cognition-first alternative to reconstruction-based planners, establishing a new direction: planning as active understanding, not passive reaction.
Paul Zaidins, Robert P. Goldman, Ugur Kuter
et al.
This paper provides theoretical and empirical comparisons of three recent hierarchical plan repair algorithms: SHOPFixer, IPyHOPPER, and Rewrite. Our theoretical results show that the three algorithms correspond to three different definitions of the plan repair problem, leading to differences in the algorithms' search spaces, the repair problems they can solve, and the kinds of repairs they can make. Understanding these distinctions is important when choosing a repair method for any given application. Building on the theoretical results, we evaluate the algorithms empirically in a series of benchmark planning problems. Our empirical results provide more detailed insight into the runtime repair performance of these systems and the coverage of the repair problems solved, based on algorithmic properties such as replanning, chronological backtracking, and backjumping over plan trees.
Lyudmila V. Glebushkina, Natalia V. Ustyugova, Polina V. Argimbaeva
The relevance of this research stems from the need to revise the content of urban planning standards for cities in Western Siberia. The focus of the study was the residential development plot as an object of urban planning regulation. The authors considered 60 residential plots in Tyumen and Omsk (30 in each city) developed between 2009 and 2019. The study aimed to identify the mutual influence of land plot size, open space morphology, and planning characteristics on the type of land development. The application of factor and cluster analyses facilitated the identification of the underlying structure within the raw data, relevant to the context of design decision-making. Factor analysis was used to group the variables from the initial dataset into a two-factor model: the first factor comprised planning indicators, and the second – morphological characteristics. Cluster analysis enabled the classification of objects based both on the variables used in the factor analysis and on the urban planning indicators employed for evaluating the design solution.
This paper considers a scenario in city navigation: an AI agent is provided with language descriptions of the goal location with respect to some well-known landmarks; By only observing the scene around, including recognizing landmarks and road network connections, the agent has to make decisions to navigate to the goal location without instructions. This problem is very challenging, because it requires agent to establish self-position and acquire spatial representation of complex urban environment, where landmarks are often invisible. In the absence of navigation instructions, such abilities are vital for the agent to make high-quality decisions in long-range city navigation. With the emergent reasoning ability of large language models (LLMs), a tempting baseline is to prompt LLMs to "react" on each observation and make decisions accordingly. However, this baseline has very poor performance that the agent often repeatedly visits same locations and make short-sighted, inconsistent decisions. To address these issues, this paper introduces a novel agentic workflow featured by its abilities to perceive, reflect and plan. Specifically, we find LLaVA-7B can be fine-tuned to perceive the direction and distance of landmarks with sufficient accuracy for city navigation. Moreover, reflection is achieved through a memory mechanism, where past experiences are stored and can be retrieved with current perception for effective decision argumentation. Planning uses reflection results to produce long-term plans, which can avoid short-sighted decisions in long-range navigation. We show the designed workflow significantly improves navigation ability of the LLM agent compared with the state-of-the-art baselines.
Recently, Large Language Models (LLMs) have emerged as an alternative to training task-specific dialog agents, due to their broad reasoning capabilities and performance in zero-shot learning scenarios. However, many LLM-based dialog systems fall short in planning towards an overarching dialog goal and therefore cannot steer the conversation appropriately. Furthermore, these models struggle with hallucination, making them unsuitable for information access in sensitive domains, such as legal or medical domains, where correctness of information given to users is critical. The recently introduced task Conversational Tree Search (CTS) proposes the use of dialog graphs to avoid hallucination in sensitive domains, however, state-of-the-art agents are Reinforcement Learning (RL) based and require long training times, despite excelling at dialog strategy. This paper introduces a novel zero-shot method for controllable CTS agents, where LLMs guide the dialog planning through domain graphs by searching and pruning relevant graph nodes based on user interaction preferences. We show that these agents significantly outperform state-of-the-art CTS agents ($p<0.0001$; Barnard Exact test) in simulation. This generalizes to all available CTS domains. Finally, we perform user evaluation to test the agent's performance in the wild, showing that our policy significantly ($p<0.05$; Barnard Exact) improves task-success compared to the state-of-the-art RL-based CTS agent.
We explore the usage of large language models (LLM) in human-in-the-loop human-in-the-plant cyber-physical systems (CPS) to translate a high-level prompt into a personalized plan of actions, and subsequently convert that plan into a grounded inference of sequential decision-making automated by a real-world CPS controller to achieve a control goal. We show that it is relatively straightforward to contextualize an LLM so it can generate domain-specific plans. However, these plans may be infeasible for the physical system to execute or the plan may be unsafe for human users. To address this, we propose CPS-LLM, an LLM retrained using an instruction tuning framework, which ensures that generated plans not only align with the physical system dynamics of the CPS but are also safe for human users. The CPS-LLM consists of two innovative components: a) a liquid time constant neural network-based physical dynamics coefficient estimator that can derive coefficients of dynamical models with some unmeasured state variables; b) the model coefficients are then used to train an LLM with prompts embodied with traces from the dynamical system and the corresponding model coefficients. We show that when the CPS-LLM is integrated with a contextualized chatbot such as BARD it can generate feasible and safe plans to manage external events such as meals for automated insulin delivery systems used by Type 1 Diabetes subjects.
Vishal Pallagani, Kaushik Roy, Bharath Muppasani
et al.
Automated Planning and Scheduling is among the growing areas in Artificial Intelligence (AI) where mention of LLMs has gained popularity. Based on a comprehensive review of 126 papers, this paper investigates eight categories based on the unique applications of LLMs in addressing various aspects of planning problems: language translation, plan generation, model construction, multi-agent planning, interactive planning, heuristics optimization, tool integration, and brain-inspired planning. For each category, we articulate the issues considered and existing gaps. A critical insight resulting from our review is that the true potential of LLMs unfolds when they are integrated with traditional symbolic planners, pointing towards a promising neuro-symbolic approach. This approach effectively combines the generative aspects of LLMs with the precision of classical planning methods. By synthesizing insights from existing literature, we underline the potential of this integration to address complex planning challenges. Our goal is to encourage the ICAPS community to recognize the complementary strengths of LLMs and symbolic planners, advocating for a direction in automated planning that leverages these synergistic capabilities to develop more advanced and intelligent planning systems.
This paper mainly reviews the fate of microplastics, released from used face masks, in the water environment. Through previous experiments, the amount of fiber microplastics released from used face masks into aqueous environments was not negligible, with the maximum microplastics releasing amount reaching 10,000 piece·day<sup>−1</sup> for each mask. Microplastic derived from these masks often occurred in the shape of polymeric fibers that resulted from the breakage of the chemical bonds in the plastic fibers by the force of water flow. The potential contact forces between microplastics (originating from face masks) with other pollutants, primarily encompass hydrophobic and electrostatic interactions. This critical review paper briefly illustrates the fate of microplastics derived from disposable face masks, further devising effective strategies to mitigate the environmental impact of plastic particle release from the used personal protective equipment.
The Hierarchical Task Network (HTN) formalism is used to express a wide variety of planning problems as task decompositions, and many techniques have been proposed to solve them. However, few works have been done on temporal HTN. This is partly due to the lack of a formal and consensual definition of what a temporal hierarchical planning problem is as well as the difficulty to develop heuristics in this context. In response to these inconveniences, we propose in this paper a new general POCL (Partial Order Causal Link) approach to represent and solve a temporal HTN problem by using existing heuristics developed to solve non temporal problems. We show experimentally that this approach is performant and can outperform the existing ones.
Autonomous agents face the challenge of coordinating multiple tasks (perception, motion planning, controller) which are computationally expensive on a single onboard computer. To utilize the onboard processing capacity optimally, it is imperative to arrive at computationally efficient algorithms for global path planning. In this work, it is attempted to reduce the processing time for global path planning in dynamically evolving polygonal maps. In dynamic environments, maps may not remain valid for long. Hence it is of utmost importance to obtain the shortest path quickly in an ever-changing environment. To address this, an existing rapid path-finding algorithm, the Minimal Construct was used. This algorithm discovers only a necessary portion of the Visibility Graph around obstacles and computes collision tests only for lines that seem heuristically promising. Simulations show that this algorithm finds shortest paths faster than traditional grid-based A* searches in most cases, resulting in smoother and shorter paths even in dynamic environments.
Existing neural radiance field-based methods can achieve real-time rendering of small scenes on the web platform. However, extending these methods to large-scale scenes still poses significant challenges due to limited resources in computation, memory, and bandwidth. In this paper, we propose City-on-Web, the first method for real-time rendering of large-scale scenes on the web. We propose a block-based volume rendering method to guarantee 3D consistency and correct occlusion between blocks, and introduce a Level-of-Detail strategy combined with dynamic loading/unloading of resources to significantly reduce memory demands. Our system achieves real-time rendering of large-scale scenes at approximately 32FPS with RTX 3060 GPU on the web and maintains rendering quality comparable to the current state-of-the-art novel view synthesis methods.
La evaluación del desempeño de los edificios (conocida como BPE, de Building Performance Evaluation, por sus siglas en inglés) es indispensable para fundamentar las decisiones de diseño. En este artículo se aborda este concepto junto a algunos estudios de casos en los que se pueden ilustrar estrategias de diseño pasivo que, aplicadas en edificios, mejoran no solo la eficiencia energética, sino que la calidad ambiental interior (o IEQ, de Indoor Environmental Quality).
Aesthetics of cities. City planning and beautifying
This manuscript focuses on analyzing the growth dynamics of the Central Taiwan Science Park (CTSP) and Silicon Glen in Scotland with a specific emphasis on their approaches to energy, environmental conservation, and economic management. The objective is to provide insights into their sustainable development strategies. In terms of energy, CTSP addresses Taiwan’s energy security and green transformation challenges, while Silicon Glen concentrates on Scotland’s wind energy generation technologies. Both regions prioritize the advancement of renewable energy sources and smart grid technologies. In the realm of environmental conservation, both CTSP and Silicon Glen prioritize environmental protection and sustainability by implementing rigorous environmental monitoring measures. Regarding economic management, CTSP and Silicon Glen serve as vital technology industry hubs in Taiwan and Scotland, respectively, attracting a multitude of high-tech and startup enterprises. This growth is facilitated through various means, including policy support, access to research resources, and robust infrastructure. This manuscript presents a comparative analysis of these two industrial parks, focusing on their environmental and economic management strategies. It aims to elucidate the principles underpinning the sustainable development and economic growth of industrial parks, offering valuable insights to decision-makers and stakeholders involved in the planning of sustainable industrial parks.
Viviane S Boaventura, Malú Grave, Thiago Cerqueira-Silva
et al.
BackgroundTelehealth has been widely used for new case detection and telemonitoring during the COVID-19 pandemic. It safely provides access to health care services and expands assistance to remote, rural areas and underserved communities in situations of shortage of specialized health professionals. Qualified data are systematically collected by health care workers containing information on suspected cases and can be used as a proxy of disease spread for surveillance purposes. However, the use of this approach for syndromic surveillance has yet to be explored. Besides, the mathematical modeling of epidemics is a well-established field that has been successfully used for tracking the spread of SARS-CoV-2 infection, supporting the decision-making process on diverse aspects of public health response to the COVID-19 pandemic. The response of the current models depends on the quality of input data, particularly the transmission rate, initial conditions, and other parameters present in compartmental models. Telehealth systems may feed numerical models developed to model virus spread in a specific region.
ObjectiveHerein, we evaluated whether a high-quality data set obtained from a state-based telehealth service could be used to forecast the geographical spread of new cases of COVID-19 and to feed computational models of disease spread.
MethodsWe analyzed structured data obtained from a statewide toll-free telehealth service during 4 months following the first notification of COVID-19 in the Bahia state, Brazil. Structured data were collected during teletriage by a health team of medical students supervised by physicians. Data were registered in a responsive web application for planning and surveillance purposes. The data set was designed to quickly identify users, city, residence neighborhood, date, sex, age, and COVID-19–like symptoms. We performed a temporal-spatial comparison of calls reporting COVID-19–like symptoms and notification of COVID-19 cases. The number of calls was used as a proxy of exposed individuals to feed a mathematical model called “susceptible, exposed, infected, recovered, deceased.”
ResultsFor 181 (43%) out of 417 municipalities of Bahia, the first call to the telehealth service reporting COVID-19–like symptoms preceded the first notification of the disease. The calls preceded, on average, 30 days of the notification of COVID-19 in the municipalities of the state of Bahia, Brazil. Additionally, data obtained by the telehealth service were used to effectively reproduce the spread of COVID-19 in Salvador, the capital of the state, using the “susceptible, exposed, infected, recovered, deceased” model to simulate the spatiotemporal spread of the disease.
ConclusionsData from telehealth services confer high effectiveness in anticipating new waves of COVID-19 and may help understand the epidemic dynamics.
Zimbabwe desperately requires financial assistance to fix existing infrastructure and build new urban water systems. This analysis suggests that PPPs may give Zimbabwe the best opportunity to overcome its problems with water infrastructure. Zimbabwe still has trouble supplying water to its cities because of a shortage of resources and deteriorating infrastructure. This situation was already confirmed by the United Nations Children's Fund (UNICEF) (see 2019 reports), and PPPs could mitigate the financial challenges to assist the Zimbabwean Government. The study utilised qualitative research to gather information. Interview responses were supplemented with a literature review to thematically state responses. The results demonstrate that political backing, government accountability, economic viability, and suitable statutory, financial, technological, and institutional frameworks are the key prerequisites for implementing PPPs effectively in Zimbabwe. The study proposes that PPPs are perceived as an alternative reform strategy for improved urban water infrastructure in the country. However, PPPs must consider the implementation imperatives before being adopted and implemented. This requires an environment conducive to operating PPPs, including proper planning and meticulous implementation. If entered hurriedly, PPPs can exacerbate the problems they were implemented to rectify, thereby saving the taxpayers' hard-earned money.
Shreya Sharma, Jigyasa Gupta, Shreshth Tuli
et al.
Our goal is to enable a robot to learn how to sequence its actions to perform tasks specified as natural language instructions, given successful demonstrations from a human partner. The ability to plan high-level tasks can be factored as (i) inferring specific goal predicates that characterize the task implied by a language instruction for a given world state and (ii) synthesizing a feasible goal-reaching action-sequence with such predicates. For the former, we leverage a neural network prediction model, while utilizing a symbolic planner for the latter. We introduce a novel neuro-symbolic model, GoalNet, for contextual and task dependent inference of goal predicates from human demonstrations and linguistic task descriptions. GoalNet combines (i) learning, where dense representations are acquired for language instruction and the world state that enables generalization to novel settings and (ii) planning, where the cause-effect modeling by the symbolic planner eschews irrelevant predicates facilitating multi-stage decision making in large domains. GoalNet demonstrates a significant improvement (51%) in the task completion rate in comparison to a state-of-the-art rule-based approach on a benchmark data set displaying linguistic variations, particularly for multi-stage instructions.
It is important to understand the characteristics of a 21st century port city in terms of the spatial relations of the city and its port. In this study, the port/city relations between the container port of Mersin in Turkey and Mersin city itself are examined. The purpose of this study is to examine which class of port city Mersin falls within and how spatial relations are established at the intersection of the port and urban area in Mersin. The Relative Concentration Index is used for evaluation at the regional scale, as used in port city classifications. The method reveals the importance of port and urban relations at a regional level in the urbanization processes of coastal cities. It is seen that Mersin Port has been at the level of a Hub since 2007 among the container ports of Turkey. ‘Hub’ is among the port city classes for which spatial planning policies in the port/city intersection area should be emphasized. It is important to integrate the revival projects with planning strategies and policies to engender a ‘living urban port area’ image for the transition zone between city and port.
Width-based search methods have demonstrated state-of-the-art performance in a wide range of testbeds, from classical planning problems to image-based simulators such as Atari games. These methods scale independently of the size of the state-space, but exponentially in the problem width. In practice, running the algorithm with a width larger than 1 is computationally intractable, prohibiting IW from solving higher width problems. In this paper, we present a hierarchical algorithm that plans at two levels of abstraction. A high-level planner uses abstract features that are incrementally discovered from low-level pruning decisions. We illustrate this algorithm in classical planning PDDL domains as well as in pixel-based simulator domains. In classical planning, we show how IW(1) at two levels of abstraction can solve problems of width 2. For pixel-based domains, we show how in combination with a learned policy and a learned value function, the proposed hierarchical IW can outperform current flat IW-based planners in Atari games with sparse rewards.
We present planning challenges, methods and preliminary results for a new model-based paradigm for earth observing systems in adaptive remote sensing. Our heuristically guided constraint optimization planner produces coordinated plans for multiple satellites, each with multiple instruments (payloads). The satellites are agile, meaning they can quickly maneuver to change viewing angles in response to rapidly changing phenomena. The planner operates in a closed-loop context, updating the plan as it receives regular sensor data and updated predictions. We describe the planner's search space and search procedure, and present preliminary experiment results. Contributions include initial identification of the planner's search space, constraints, heuristics, and performance metrics applied to a soil moisture monitoring scenario using spaceborne radars.