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.

Stochastic shortest path (SSP) problems are a common framework for planning under uncertainty. However, the reactive structure of their solution policies is typically not easily comprehensible by an end-user, nor do planners justify the reasons behind their choice of a particular policy over others. To strengthen confidence in the planner's decision-making, recent work in classical planning has introduced a framework for explaining to the user the possible solution space in terms of necessary trade-offs between user-provided plan properties. Here, we extend this framework to SSPs. We introduce a notion of policy properties taking into account action-outcome uncertainty. We analyze formally the computational problem of identifying the exclusion relationships between policy properties, showing that this problem is in fact harder than SSP planning in a complexity theoretical sense. We show that all the relationships can be identified through a series of heuristic searches, which, if ordered in a clever way, yields an anytime algorithm. Further, we introduce an alternative method, which leverages a connection to multi-objective probabilistic planning to move all the computational burden to a preprocessing step. Finally, we explore empirically the feasibility of the proposed explanation methodology on a range of adapted IPPC benchmarks.

Critical software systems require stringent testing to identify possible failure cases, which can be difficult to find using manual testing. In this study, we report our industrial experience in testing a realistic R&D flight control system using a heuristic based testing method. Our approach utilizes evolutionary strategies augmented with intrinsic motivation to yield a diverse range of test cases, each revealing different potential failure scenarios within the system. This diversity allows for a more comprehensive identification and understanding of the system’s vulnerabilities. We analyze the test cases found by evolution to identify the system’s weaknesses. The results of our study show that our approach can be used to improve the reliability and robustness of avionics systems by providing high-quality test cases in an efficient and cost-effective manner.

The ability to perform different skills can encourage agents to explore. In this work, we aim to construct a set of diverse skills that uniformly cover the state space. We propose a formalization of this search for diverse skills, building on a previous definition based on the mutual information between states and skills. We consider the distribution of states reached by a policy conditioned on each skill and leverage the successor state representation to maximize the difference between these skill distributions. We call this approach LEADS: Learning Diverse Skills through Successor State Representations. We demonstrate our approach on a set of maze navigation and robotic control tasks which show that our method is capable of constructing a diverse set of skills which exhaustively cover the state space without relying on reward or exploration bonuses. Our findings demonstrate that this new formalization promotes more robust and efficient exploration by combining mutual information maximization and exploration bonuses.

Width-based planning algorithms have been demonstrated to be competitive with state-of-the-art heuristic search and SAT-based approaches, without requiring access to a model of action effects and preconditions, just access to a black-box simulator. Width-based planners search is guided by a measure of the novelty of states, that requires observations on simulator states to be given as a set of features. This paper proposes agnostic feature mapping mechanisms that define the features online, as exploration progresses and the domain of continuous state variables is revealed. We demonstrate the effectiveness of these features on the OpenAI gym "classical control" suite of benchmarks. We compare our online planners with state-of-the-art deep reinforcement learning algorithms, and show that width-based planners using our features can find policies of the same quality with significantly less computational resources.

Mission planning for Earth Observation Satellite operators typically implies dynamically altering how requests from different customers are prioritised in order to meet expected deadlines. A request corresponds to a given area of interest to capture on Earth. This exercise is challenging for different reasons. First, satellites are limited by maneuvers and power consumption constraints resulting in a limited surface that can be covered at each orbit. Consequently, many requests are in competition with each other and so all of them cannot be treated at each orbit. When a request priority is boosted, it may incidentally penalise surrounding requests. Second, there are several uncertain factors such as weather (in particular cloud cover) and future incoming requests that can impact the completion progress of the requests. With order books of increasing size and the planned operations of a growing number of satellites in a close future, there is a clear need for a decision support method.

Qualitative Possibilistic Mixed-Observable MDPs (pi-MOMDPs), generalizing pi-MDPs and pi-POMDPs, are well-suited models to planning under uncertainty with mixed-observability when transition, observation and reward functions are not precisely known and can be qualitatively described. Functions defining the model as well as intermediate calculations are valued in a finite possibilistic scale L, which induces a finite belief state space under partial observability contrary to its probabilistic counterpart. In this paper, we propose the first study of factored pi-MOMDP models in order to solve large structured planning problems under qualitative uncertainty, or considered as qualitative approximations of probabilistic problems. Building upon the SPUDD algorithm for solving factored (probabilistic) MDPs, we conceived a symbolic algorithm named PPUDD for solving factored pi-MOMDPs. Whereas SPUDD's decision diagrams' leaves may be as large as the state space since their values are real numbers aggregated through additions and multiplications, PPUDD's ones always remain in the finite scale L via min and max operations only. Our experiments show that PPUDD's computation time is much lower than SPUDD, Symbolic-HSVI and APPL for possibilistic and probabilistic versions of the same benchmarks under either total or mixed observability, while still providing high-quality policies.

In many probabilistic planning scenarios, a system’s behavior needs to not only maximize the expected utility but also obey certain restrictions. This paper presents Saturated Path-Constrained Markov Decision Processes (SPC MDPs), a new MDP type for planning under uncertainty with deterministic model-checking constraints, e.g., "state s must be visited befores s'", "the system must end up in s", or "the system must never enter s". We present a mathematical analysis of SPCMDPs, showing that although SPC MDPs generally have no optimal policies, every instance of this class has an epsilon-optimal randomized policy for any > 0. We propose a dynamic programming-based algorithm for finding such policies, and empirically demonstrate this algorithm to be orders of magnitude faster than its next-best alternative.

This paper tackles high-level decision-making techniques for robotic missions, which involve both active sensing and symbolic goal reaching, under uncertain probabilistic environments and strong time constraints. Our case study is a POMDP model of an online multi-target detection and recognition mission by an autonomous UAV. The POMDP model of the multi-target detection and recognition problem is generated online from a list of areas of interest, which are automatically extracted at the beginning of the flight from a coarse-grained high altitude observation of the scene. The POMDP observation model relies on a statistical abstraction of an image processing algorithm's output used to detect targets. As the POMDP problem cannot be known and thus optimized before the beginning of the flight, our main contribution is an "optimize-while-execute" algorithmic framework: it drives a POMDP sub-planner to optimize and execute the POMDP policy in parallel under action duration constraints. We present new results from real outdoor flights and SAIL simulations, which highlight both the benefits of using POMDPs in multi-target detection and recognition missions, and of our "optimize-while-execute" paradigm.

Optimal solutions to Stochastic Shortest Path Problems (SSPs) usually require that there exists at least one policy that reaches the goal with probability 1 from the initial state. This condition is very strong and prevents from solving many interesting problems, for instance where all possible policies reach some dead-end states with a positive probability. We introduce a more general and richer dual optimization criterion, which minimizes the average (undiscounted) cost of only paths leading to the goal among all policies that maximize the probability to reach the goal. We present policy update equations in the form of dynamic programming for this new dual criterion, which are different from the standard Bellman equations, but produce the same solution if there exists one policy leading to the goal with probability 1 from the initial state. We demonstrate that our equations converge in infinite horizon without any condition on the structure of the problem or on its policies, which actually extends the class of SSPs that can be solved. We experimentally show that our dual criterion provides well-founded solutions to SSPs that can not be solved by the standard criterion, and that using a discount factor with the latter certainly provides solution policies but which are not optimal considering our well-founded criterion.

Recent domain-determinization techniques have been very successful in many probabilistic planning problems. We claim that traditional heuristic MDP algorithms have been unsuccessful due mostly to the lack of efficient heuristics in structured domains. Previous attempts like mGPT used classical planning heuristics to an all-outcome determinization of MDPs without discount factor; yet, discounted optimization is required to solve problems with potential dead-ends. We propose a general extension of classical planning heuristics to goal-oriented discounted MDPs, in order to overcome this flaw. We apply our theoretical analysis to the well-known classical planning heuristics Hmax and Hadd, and prove that the extended Hmax is admissible. We plugged our extended heuristics to popular graph-based (Improved-LAO*, LRTDP, LDFS) and ADD-based (sLAO*, sRTDP) MDP algorithms: experimental evaluations highlight competitive results compared with the winners of previous competitions (FF-Replan, FPG, RFF), and show that our discounted heuristics solve more problems than non-discounted ones, with better criteria values. As for classical planning, the extended Hadd outperforms the extended Hmax on most problems.

Robotic missions require to implement various functionalities in order to link reactive functions at actuators and sensors level to deliberative functions like vision, supervision and planning at decisional level. All these functionalities must be versatile and generic enough to interact differently according to the missions while minimizing recoding effort. Moreover, deliberative functions like automated planning consume lots of memory and CPU time and usually complete in time incompatible with robotic missions' durations. Thus, we present a new generic and anytime planning concept for modular robotic architectures, which manages multiple planning requests at a time, solved in background, while allowing for reactive execution of planned actions at the same time. Different planners based on various formalisms and data structures can be plugged to the planning component without changing its behavior nor its code, facilitating reusability and validation of the component. We highlight the versatility of our concept on different use cases; then we demonstrate the efficiency of our approach in terms of mission duration and success, compared with traditional plan-then-execute approaches; we finally present a search and rescue mission by an autonomous rotorcraft solved with our paradigm, that cannot be tackled by traditional approaches.