Association for the Advancement of Artificial Intelligence: AAAI Publications
Not a member yet
26155 research outputs found
Sort by
AI Ethics for Creativity
No full textAI Ethics for Creativity is a study of lived experience under the overarching theme of creative expression through new technologies--the new technology being AI. In this context, I reference the past, situate the present, and speculate on the future. The nature of the dissertation is to ask ``humanities'' questions from the lens of Human-Computer Interaction, i.e. what is creativity, interaction, art, aesthetics, embodiment, and expression... with AI in the creative endeavor
Making Sense of Digital Domination
No full textThe republican concept of domination in the context of the digital realm has increasingly gained attention. Domination is an instance of superior and arbitrary power. While the discussions on digital domination are a worthwhile expansion of AI Ethics, much of the debate remains limited to online platforms and specific to a particular relation or context. In this paper, I follow Pettit’s account of domination to argue that certain seemingly more innocent AI systems dominate citizens of digital societies. I claim that in such societies, basic liberties, i.e., liberties required to function equally in society, increasingly depend on AI systems that cannot be held to account due to ineffective regulation. This constitutes an arbitrary power relation (i.e., domination) between the AI and the person subjected to the AI. Given basic liberties apply to any citizen of a particular society, all citizens living in modern, digital societies are dominated. Digital domination, therefore, has much broader societal implications than is currently acknowledged in the literature. I conclude by proposing what I believe to be the root source of this digital domination: an ‘innovation-friendly’ approach enabled by socio-economic structures
On the Notion of Plan Quality for PDDL+
No full textPDDL+ is a planning formalism designed to model mixed continuous-discrete problems. Despite its expressiveness, the absence of a well-established framework for evaluating plan quality makes it challenging to use PDDL+ in applications where plan shape and quality are crucial.
This paper addresses this issue by introducing a comprehensive set of plan cost functions tailored for discrete-time PDDL+, along with a cost-preserving translation for generating cost-aware PDDL2.1 planning tasks.
The plan cost functions provide a theoretical ground for assessing plan quality, whereas the translation shows their practicability by leveraging the connection between PDDL+ and PDDL2.1
A Sampling Approach to Planning with Infinite Domain Control Variables
No full textResearch in planning has sought to broaden the scope of planning problems by incorporating numeric parameters into action descriptions to condition both continuous and discrete change. Focusing on the latter, this work studies the problem of numeric planning with control variables, a reformulation of actions with infinite domain parameters. To tackle the challenge of handling an infinite decision space driven by control variables, we incorporate sampling into a forward state-space search. The resulting search framework (1) partially expands nodes by sampling their successors and (2) implements a re-expansion strategy to sample additional successors if a node shows promise in future evaluations. We perform a deep probe into this concept that materializes into a new algorithm called Sampling Greedy Best-First Search (S-GBFS). Our empirical evaluation of S-GBFS across various domains shows significant improvements over existing planning approaches
New Mechanisms in Flex Distribution for Bounded Suboptimal Multi-Agent Path Finding
No full textMulti-Agent Path Finding (MAPF) is the problem of finding a set of collision-free paths, one for each agent in a shared environment. Its objective is to minimize the sum of path costs (SOC), where the path cost of each agent is defined as the travel time from its start location to its target location. Explicit Estimation Conflict-Based Search (EECBS) is the leading algorithm for bounded-suboptimal MAPF, with the SOC of the solution being at most a user-specified factor w away from optimal. EECBS maintains sets of paths and a lower bound LB on the optimal SOC. Then, it iteratively selects a set of paths whose SOC is at most w times LB and introduces constraints to resolve collisions. For each path in a set, EECBS maintains a lower bound on its optimal path that satisfies constraints. By finding a path with cost at most its threshold, defined as w times its lower bound, EECBS guarantees to find a bounded-suboptimal solution. To speed up EECBS, previous work uses flex distribution to relax the requirement that each path needs to be at most its threshold. Though EECBS with flex distribution guarantees to find a bounded-suboptimal solution, increasing the thresholds may increase the SOC beyond w times LB, forcing EECBS to switch among different sets of paths (whose SOC are still at most w times LB), and thus reducing efficiency. To address this issue, we propose Conflict-Based Flex Distribution that distributes flex in proportion to the number of collisions. We also estimate the extra travel time (i.e., delays) needed to satisfy constraints and propose Delay-Based Flex Distribution. On top of that, we propose Mixed-Strategy Flex Distribution, combining both in a hierarchical framework. We prove that EECBS with our new flex distribution mechanisms is complete and bounded-suboptimal. The experiments show that our approaches outperform the original (greedy) flex distribution. Also, we redesign Focal-A* search from the previous work to improve LB for a congested environment
Real-time Cost-algebraic Heuristic Search
No full textPlanning under time pressure arises in many situations. Real-time heuristic search, in which an agent must compute its next action within a prespecified time bound, has proven to be a useful model of real-time planning. However, it is laborious to prove the completeness of new real-time search algorithms. In this paper, we provide a general proof of the completeness of a standard real-time heuristic search algorithm in any problem domain that obeys the axioms of a cost algebra. The proof includes additional detail on how h values change as the algorithm learns. This foundation clarifies the dependence of the proof on domain and algorithm properties and will ease future applications of real-time planning
Guiding the Search for the Euclidean Shortest Path Problem
No full textWe consider the problem of reducing the search space of algorithms which solve the Euclidean Shortest Path Problem by traversing a precomputed navigation mesh. Heuristics can be used to guide this traversal. We show how upper and lower bounds to the optimal path length can be combined into an independent heuristic which considerably reduces the search space of such an algorithm. In our experiments we use our heuristic in an existing routing algorithm and find that our approach yields a substantial speedup for complicated paths
Object Packing and Scheduling for Sequential 3D Printing: A Linear Arithmetic Model and a CEGAR-Inspired Optimal Solver (Extended Abstract)
No full textWe address the problem of object arrangement and scheduling for sequential 3D printing. Unlike the standard 3D printing, where all objects are printed slice by slice, in sequential 3D printing, objects are completed one after another. In the sequential case, it is necessary to ensure that the moving parts of the printer do not collide with previously printed objects. We propose to express the problem of sequential printing as a linear arithmetic formula, which is then solved using a solver for satisfiability modulo theories (SMT) combined with counterexample guided abstraction refinement (CEGAR)
A2S-AFLNet: An Adaptive Bat Optimized Two-Stage Attention Fused LSTM Networks for Attack-Resilient Intrusion Detection
No full textWith the increasing sophistication of cyber security risks, utilizing machine learning algorithms alongside intrusion detection systems has become crucial. Conventional approaches to detection intrusion on network traffic data come with limitations such as higher false positive rates, inability to adapt evolving attack patterns, and ineffective handling of large data volume. Deep neural networks such as long short-term memory (LSTMs) are good at understanding patterns in network data over time. Sometimes, they overlook aspects that can cause unnecessary calculations, which leads to less optimal detection results. We present an adaptive bat-optimized and two-stage LSTM network fused with attention (A2S-AFLNet) to address these issues. This method combines attention mechanisms and LSTM to improve feature selection while also making the learning process more efficient and adaptable for intrusion detection. Standard performance metrics were analyzed and compared with the recent machine learning and neural network-based IDS models using the UNSW-NB15 dataset to validate the robustness of the framework
Multi-Scale Unrectified Push-Pull with Channel Attention for Enhanced Corruption Robustness
No full textConvolutional Neural Networks (CNNs) have achieved remarkable success in computer vision tasks, however, they often experience substantial performance degradation when confronted with real-world corruptions such as noise, compression artifacts, and lighting variations. The original push–pull CNN (PP-CNN) architecture addresses this challenge by employing a biologically inspired mechanism that contrasts local excitatory (push) and broader inhibitory (pull) responses to suppress noise. In this work, we enhance the robustness of PP-CNN through three key modifications: (1) removing the half-wave rectification constraint to enable more expressive interactions between push and pull signals, allowing for richer linear feature enhancement; (2) introducing a dynamic channel attention mechanism that adaptively recalibrates feature responses by amplifying discriminative signals and suppressing noise-dominated channels; and (3) designing a multi-scale push–pull (MSPP) framework that searches for pattern consistency across multiple spatial resolutions, reinforcing the model’s ability to generalize under corruptions at varying scales.
Our proposed enhancements introduce a stronger inductive bias toward learning scale-consistent features—a fundamental property of natural images that remains stable even under corruption—without requiring corruption-specific data augmentation. Comprehensive evaluations on the CIFAR-10-C benchmark demonstrate that the enhanced PP-CNN achieves improvements in robustness across diverse corruption types while maintaining competitive accuracy on clean data. Notably, the multi-scale variant delivers the best trade-off between robustness and clean data performance, demonstrating the effectiveness of exploiting multi-scale feature consistency for generalization to unseen common image corruptions