An official website of the United States government
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. We aim to keep the categorization of papers updated on https://ai4society.github.io/LLM-Planning-Viz/, a collaborative resource that allows researchers to contribute and add new literature to the categorization.
more »
« less
Race, Planning, and Emergency Management: Combating Inequities in Community Planning Policies
Disaster preparedness and relief is a key service provided by the American system of government, but emergency management practices have produced varying outcomes. Based on the existing literature, emergency management, community planning, and a history of racial inequities are inextricably interconnected. Based on the concepts presented by social equity, community planning, emergency management, and environmental policy literature, an interdisciplinary approach was used to create an original checklist of considerations for emergency managers, community planners, and policymakers to use in a collaborative manner to proactively address potential threats to their constituents and communities.
more »
« less
- Award ID(s):
- 1922687
- PAR ID:
- 10457952
- Publisher / Repository:
- SAGE Publications
- Date Published:
- Journal Name:
- Journal of Planning Literature
- Volume:
- 39
- Issue:
- 2
- ISSN:
- 0885-4122
- Format(s):
- Medium: X Size: p. 175-185
- Size(s):
- p. 175-185
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We describe a framework for deploying agent-based models as a tool for decision-making during resilience planning, with an emphasis on flood mitigation. Prior work has demonstrated that agent-based models can be effective tools for modelling evolving community flood resilience and risk perception when they incorporate elements of individual decision-making. We argue for extending this methodology and incorporating it into regional infrastructure and resilience planning in order to 1) create more distributed and robust green infrastructure implementations and performance management systems; 2) provide a critique and alternatives to existing planning and delivery processes based on public sector jurisdictional boundaries; and, 3) validate and improve the modelling process by connecting it directly to stakeholder decision-making processes. This final point will effectively merge these systems-centric modelling approaches with human-centred community organising that employs various co-design methods. In regard to the ABMs, co-design methods can be a useful source of real-world data about individual decision-making that can inform and validate iterations of the models. For stakeholders, they can be a valuable source of information and education about flood risk and climate-related impacts that might not be available through other channels. And finally, hands-on workshops coupled with potential small implementation grants can be effective ways of providing skills and incentives to stakeholders who may wish to undertake projects on their own property, reshaping the way green infrastructure planning and implementation can be accomplished.more » « less
-
Abstract High-speed broadband internet is a necessary utility. However, internet service providers are often unwilling to take on the costs of serving rural areas. Federal investments to expand rural broadband have gone underutilized due to insufficient community awareness and planning practices. We explore university–community broadband planning in two rural Florida counties to demonstrate where partnership and local efforts have enabled constructive discussions toward better connectivity. We highlight similarities and differences that inform how the university and residents leveraged community capital, and we explore the planning practices employed in each case. We conclude with recommendations for community-based partnerships for broadband planning in rural communities.more » « less
-
Abstract Theory predicts that effective environmental governance requires that the scales of management account for the scales of environmental processes. A good example is community wildfire protection planning. Plan boundaries that are too narrowly defined may miss sources of wildfire risk originating at larger geographic scales whereas boundaries that are too broadly defined dilute resources. Although the concept of scale (mis)matches is widely discussed in literature on risk mitigation as well as environmental governance more generally, rarely has the concept been rigorously quantified. We introduce methods to address this limitation, and we apply our approach to assess scale matching among Community Wildfire Protection Plans (CWPPs) in the western US. Our approach compares two metrics: (1) the proportion of risk sources encompassed by planning jurisdictions (sensitivity) and (2) the proportion of area in planning jurisdictions in which risk can originate (precision). Using data from 852 CWPPs and a published library of 54 million simulated wildfires, we demonstrate a trade-off between sensitivity and precision. Our analysis reveals that spatial scale match—the product of sensitivity and precision—has an n-shaped relationship with jurisdiction size and is maximal at approximately 500 km2. Bayesian multilevel models further suggest that functional scale match—via neighboring, nested, and overlapping planning jurisdictions—may compensate for low sensitivity. This study provides a rare instance of a quantitative framework to measure scale match in environmental planning and has broad implications for risk mitigation as well as in other environmental governance settings.more » « less
-
This paper presents an integrated motion planning system for autonomous vehicle (AV) parking in the presence of other moving vehicles. The proposed system includes 1) a hybrid environment predictor that predicts the motions of the surrounding vehicles and 2) a strategic motion planner that reacts to the predictions. The hybrid environment predictor performs short-term predictions via an extended Kalman filter and an adaptive observer. It also combines short-term predictions with a driver behavior cost-map to make long-term predictions. The strategic motion planner comprises 1) a model predictive control-based safety controller for trajectory tracking; 2) a search-based retreating planner for finding an evasion path in an emergency; 3) an optimization-based repairing planner for planning a new path when the original path is invalidated. Simulation validation demonstrates the effectiveness of the proposed method in terms of initial planning, motion prediction, safe tracking, retreating in an emergency, and trajectory repairing.more » « less
