This paper presents the demonstrator developed in the TUPLES European Union research project for assisting human operators at Airbus to plan Beluga cargo ground logistic operations. The demonstrator features techniques providing robust, explainable, and safe decisions, which all contribute to making our decision-support system trusted by the operators. We have also worked on various planning methods to scale up to the size of the real industrial problem, including hybrid machine learning and symbolic algorithms. We demonstrate the software that was tested by Airbus operators during a user study in Finkenwerder’s production site in May 2025.

Heuristic search is a prominent method for plan generation in classical planning. Here we address its use for a new problem that we baptize action optimality checking (AOC): checking whether a given action a is optimal in a given state s. AOC has various potential uses, e.g. quality assurance for learned action policies through checking example policy decisions. A vanilla algorithm for AOC is to run two A⋆ searches, on each of s and the outcome state s′ of applying a. We show that one can do much better than this. We introduce early termination criteria across multiple searches. Beyond this, we introduce AOCA⋆, which performs a single search on s that gives preference to paths going through s′. Our experiments show that AOCA⋆ is superior to the vanilla algorithm as well as other multiple-search configurations, consistently across three different state-of-the-art heuristic functions.

Testing is a natural approach to assess the quality of learned action policies π. Prior work introduced policy testing in AI planning as searching for bugs in π, that is, states where π is sub-optimal with respect to a given testing objective. Beyond quality assurance, an obvious application of these methods is policy selection: given several π to choose from, we can use testing to select the "least buggy" one. Here, we integrate testing-based policy selection into the training process. This includes making more informed decisions when selecting the final policy after training, as well as choosing more promising intermediate policies during the training process. Our experiments with ASNets action policies show that integrating testing allows us to more reliably obtain good-quality policies.

Testing was recently proposed as a method to gain trust in learned action policies in classical planning. Test cases in this setting are states generated by a fuzzing process that performs random walks from the initial state. A fuzzing bias attempts to bias these random walks towards policy bugs, that is, states where the policy performs sub-optimally. Prior work explored a simple fuzzing bias based on policy-trace cost. Here, we investigate this topic more deeply. We introduce three new fuzzing biases based on analyses of policy-trace shape, estimating whether a trace is close to looping back on itself, whether it contains detours, and whether its goal-distance surface does not smoothly decline. Our experiments with two kinds of neural action policies show that these new biases improve bug-finding capabilities in many cases.

Abstract Decoupled search is a state space search method originally introduced in AI Planning. Similar to partial-order reduction methods, decoupled search exploits the independence of components to tackle the state explosion problem. Similar to symbolic representations, it does not construct the explicit state space, but sets of states are represented in a compact manner, exploiting component independence. Given the success of both partial-order reduction and symbolic representations when model checking liveness properties, our goal is to add decoupled search to the toolset of liveness checking methods. Specifically, we show how decoupled search can be applied to liveness verification for composed Büchi automata by adapting, and showing correct, a standard algorithm for detecting lassos (i.e., infinite accepting runs), namely nested depth-first search. We evaluate our approach using a prototype implementation.