Overview

Symbolic planning represents goals, states, and actions explicitly so a system can search for action sequences that achieve a goal. Common approaches use STRIPS or PDDL models with heuristic search, SAT or SMT solving, and hierarchical task planning; other work learns action models and search heuristics. Neuro-symbolic systems connect language and vision models to symbolic planners for robotics, using verification, execution feedback, and replanning to handle real-world tasks. A central challenge is balancing scalable, generalizable planning with reliable grounding and execution when models or observations are incomplete, as evaluations range from IPC benchmarks and puzzles to household robotics.

Latest papers

92 papers4 papers in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

May 19, 2025

ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models

Integrating Large Language Models with symbolic planners is a promising direction for obtaining verifiable and grounded plans, with recent works extending this idea to visual domains using Vision-Language Models (VLMs). However, an open-source benchmark for comparing these approaches under matched conditions is missing, due to a lack of visual benchmarks that support symbolic planning. We present ViPlan, the first open-source benchmark for comparing VLM-grounded symbolic approaches (VLM-as-grounder) with direct VLM planning methods (VLM-as-planner). ViPlan introduces a series of increasingly challenging tasks in two visual domains: a visual variant of the classic Blocksworld planning problem and a simulated household robotics environment. Averaged across methods, we find VLM-as-grounders to outperform direct VLM planning in Blocksworld (solving 46% of the tasks against 9%), where image grounding is both crucial and accurate. However, in the household robotics tasks, where linguistic knowledge helps, VLM-as-planner methods are greatly superior to VLM-as-grounder approaches (solving 34% of the tasks against 5%), which are hindered by partial observability. Thus, ViPlan domains capture fundamental shortcomings of both planning approaches, which we further diagnose with a qualitative failure analysis. Finally, across methods, we observe no consistent benefit from Chain-of-Thought prompting, suggesting persistent limitations in current VLMs' visual reasoning abilities.
Feb 5, 2024

Decidable Reasoning About Time in Finite-Domain Situation Calculus Theories

Representing time is crucial for cyber-physical systems and has been studied extensively in the situation calculus. The most commonly used approach represents time by adding a real-valued function time(a)\mathit{time}(a) that attaches a time point to each action and consequently to each situation. We show that in this approach, checking whether there is a reachable situation that satisfies a given formula is undecidable, even when the domain contains only finitely many objects. We present an alternative approach based on well-established results from timed automata theory by introducing clocks as real-valued fluents with restricted successor state axioms and comparison operators. With this restriction, we can show that the reachability problem for finite-domain basic action theories is decidable. Finally, we apply our results to Golog program realization by presenting a decidable procedure for determining an action sequence that is a successful execution of a given program.