No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Explaining Autonomous Drones: An XAI Journey
Abstract
COGLE (COmmon Ground Learning and Explanation) is an explainable artificial intelligence (XAI) system where autonomous drones deliver supplies to field units in mountainous areas. The mission risks vary with topography, flight decisions, and mission goals. The missions engage a human plus AI team where users determine which of two AI-controlled drones is better for each mission. This paper reports on the technical approach and findings of the project and reflects on challenges that complex combinatorial problems present for users, machine learning, user studies, and the context of use for XAI systems. COGLE creates explanations in multiple modalities. Narrative “What” explanations compare what each drone does on a mission and “Why” based on drone competencies determined from experiments using counterfactuals. Visual “Where” explanations highlight risks on maps to help users to interpret flight plans. One branch of the research studied whether the explanations helped users to predict drone performance. In this branch, a model induction user study showed that post-decision explanations had only a small effect in teaching users to determine by themselves which drone is better for a mission. Subsequent reflection suggests that supporting human plus AI decision making with pre-decision explanations is a better context for benefiting from explanations on combinatorial tasks.
This article is protected by copyright. All rights reserved.
... Among such associated with technology challenges are several. For example, operational Artificial Intelligence (AI), which, while assisting the flight, is not responsible for making ethical decisions in the cases of a rapidly escalating problem that may lead to a crash [42]. BVLOS and VTOL operations are heavily controlled by the on-board automation that relies on sensors and may engage the operating AI. ...
The Arctic is one of the least developed and most under-invested regions in the world, primarily due to its harsh environment and remoteness. However, with the current retreat of Arctic sea ice, the pristine Arctic region is gradually open for economic activities and has been of great interest for Arctic council members. For example, the European Union (EU) Integrated Policy for the Arctic has a clear emphasis on the issues specific to the European Arctic. In particular, it focuses on sustainable Arctic maritime economic growth and launches a process of identifying and developing its relevant key enabling technologies. Unmanned Aircraft System (UAS) or drone is a key enabling technology for missions in harsh and remote Arctic environment, such as finding shorter and safer shipping routes, geological survey for undiscovered rare earth elements, delivering medical supplies to remote areas, Search & Rescue operations, and tracking Arctic ice and vegetation for climate change study. In this paper, we present challenges, opportunities, and enabling technologies related to the development of UAS for Arctic applications. Furthermore, we discuss our hands-on experience of flying drones in harsh Arctic environment and provide a list of operational risks and recommendations.
The vision of AI collaborators has long been a staple of science fiction, where artificial agents understand nuances of collaboration and human communication. They bring advantages to their human collaborators and teams by contributing their special talents. Government advisory groups and leaders in AI have advocated for years that AIs should be human compatible and be capable of effective collaboration. Nonetheless, robust AIs that can collaborate like talented people remain out of reach. This position paper draws on a cognitive analysis of what effective and robust collaboration requires of human and artificial agents. It sketches a history of public and AI visions for artificial collaborators, starting with early visions of intelligence augmentation (IA) and artificial intelligence (AI). It is intended as motivation and context for a second position paper on collaborative AI (Stefik & Price, 2023). The second paper reviews the multi-disciplinary state-of-the-art and proposes a roadmap for bootstrapping collaborative AIs.
DARPA formulated the Explainable Artificial Intelligence (XAI) program in 2015 with the goal to enable end users to better understand, trust, and effectively manage artificially intelligent systems. In 2017, the four-year XAI research program began. Now, as XAI comes to an end in 2021, it is time to reflect on what succeeded, what failed, and what was learned. This article summarizes the goals, organization, and research progress of the XAI Program.
DARPA formulated the Explainable Artificial Intelligence (XAI) program in 2015 with the goal to enable end users to better understand, trust, and effectively manage artificially intelligent systems. In 2017, the four-year XAI research program began. Now, as XAI comes to an end in 2021, it is time to reflect on what succeeded, what failed, and what was learned. This article summarizes the goals, organization, and research progress of the XAI Program.
Advances in computer technology and increasing usage of computer graphics in a broad field of applications lead to rapidly rising demands regarding size and detail of virtual landscapes. Manually creating huge, realistic looking terrains and populating them densely with assets is an expensive and laborious task. In consequence, (semi-)automatic procedural terrain generation is a popular method to reduce the amount of manual work. However, such methods are usually highly specialized for certain terrain types and especially the procedural generation of landscapes composed of different biomes is a scarcely explored topic. We present a novel system, called AutoBiomes, which is capable of efficiently creating vast terrains with plausible biome distributions and therefore different spatial characteristics. The main idea is to combine several synthetic procedural terrain generation techniques with digital elevation models (DEMs) and a simplified climate simulation. Moreover, we include an easy-to-use asset placement component which creates complex multi-object distributions. Our system relies on a pipeline approach with a major focus on usability. Our results show that our system allows the fast creation of realistic looking terrains.
The process of explaining something to another person is more than offering a statement. Explaining means taking the perspective and knowledge of the Learner into account, and determining whether the Learner is satisfied. While the nature of explanationconceived of as a set of statements has been explored philosophically, empirically, and experimentally, the process of explaining, as an activity, has received less attention. We conducted a naturalistic study, looking at 74 cases of explaining. The results imply three models: local explaining about why a device (such an intelligent system) acted in a surprising way, global explaining about how a device works, and self-explaining in which people craft their own understanding. The examination of the process of explaining as it occurs in natural settings helped us to identify a number of mistaken beliefs about how explaining works.
In this paper we present a broad overview of the last 40 years of research on cognitive architectures. To date, the number of existing architectures has reached several hundred, but most of the existing surveys do not reflect this growth and instead focus on a handful of well-established architectures. In this survey we aim to provide a more inclusive and high-level overview of the research on cognitive architectures. Our final set of 84 architectures includes 49 that are still actively developed, and borrow from a diverse set of disciplines, spanning areas from psychoanalysis to neuroscience. To keep the length of this paper within reasonable limits we discuss only the core cognitive abilities, such as perception, attention mechanisms, action selection, memory, learning, reasoning and metareasoning. In order to assess the breadth of practical applications of cognitive architectures we present information on over 900 practical projects implemented using the cognitive architectures in our list. We use various visualization techniques to highlight the overall trends in the development of the field. In addition to summarizing the current state-of-the-art in the cognitive architecture research, this survey describes a variety of methods and ideas that have been tried and their relative success in modeling human cognitive abilities, as well as which aspects of cognitive behavior need more research with respect to their mechanistic counterparts and thus can further inform how cognitive science might progress.
This paper introduces SC2LE (StarCraft II Learning Environment), a reinforcement learning environment based on the StarCraft II game. This domain poses a new grand challenge for reinforcement learning, representing a more difficult class of problems than considered in most prior work. It is a multi-agent problem with multiple players interacting; there is imperfect information due to a partially observed map; it has a large action space involving the selection and control of hundreds of units; it has a large state space that must be observed solely from raw input feature planes; and it has delayed credit assignment requiring long-term strategies over thousands of steps. We describe the observation, action, and reward specification for the StarCraft II domain and provide an open source Python-based interface for communicating with the game engine. In addition to the main game maps, we provide a suite of mini-games focusing on different elements of StarCraft II gameplay. For the main game maps, we also provide an accompanying dataset of game replay data from human expert players. We give initial baseline results for neural networks trained from this data to predict game outcomes and player actions. Finally, we present initial baseline results for canonical deep reinforcement learning agents applied to the StarCraft II domain. On the mini-games, these agents learn to achieve a level of play that is comparable to a novice player. However, when trained on the main game, these agents are unable to make significant progress. Thus, SC2LE offers a new and challenging environment for exploring deep reinforcement learning algorithms and architectures.
We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard reinforcement learning algorithms and show that parallel actor-learners have a stabilizing effect on training allowing all four methods to successfully train neural network controllers. The best performing method, an asynchronous variant of actor-critic, surpasses the current state-of-the-art on the Atari domain while training for half the time on a single multi-core CPU instead of a GPU. Furthermore, we show that asynchronous actor-critic succeeds on a wide variety of continuous motor control problems as well as on a new task involving finding rewards in random 3D mazes using a visual input.
This paper describes mechanisms for asynchronous collaboration in the context of information visualization, recasting visualizations as not just analytic tools, but social spaces. We contribute the design and implementation of sense.us, a web site supporting asynchronous collaboration across a variety of visualization types. The site supports view sharing, discussion, graphical annotation, and social navigation and includes novel interaction elements. We report the results of user studies of the system, observing emergent patterns of social data analysis, including cycles of observation and hypothesis, and the complementary roles of social navigation and data-driven exploration.
This article describes mechanisms for asynchronous collaboration in the context of information visualization, recasting visualizations as not just analytic tools, but social spaces. We contribute the design and implementation of sense. us, a Web site supporting asynchronous collaboration across a variety of visualization types. The site supports view sharing, discussion, graphical annotation, and social navigation and includes novel interaction elements. We report the results of user studies of the system, observing emergent patterns of social data analysis, including cycles of observation and hypothesis, and the complementary roles of social navigation and data-driven exploration.
The DENDRAL Project was one of the first large-scale programs to embody the strategy of using detailed, task-specific knowledge about a problem domain as a source of heuristics, and to seek generality through automating the acquisition of such knowledge. This paper summarizes the major conceptual contributions and accomplishments of that project. It is an attempt to distill from this research the lessons that are of importance to artificial intelligence research and to provide a record of the final status of two decades of work. Peer Reviewed http://deepblue.lib.umich.edu/bitstream/2027.42/30758/1/0000409.pdf
Although the problem of determining the minimum cost path through a graph arises naturally in a number of interesting applications, there has been no underlying theory to guide the development of efficient search procedures. Moreover, there is no adequate conceptual framework within which the various ad hoc search strategies proposed to date can be compared. This paper describes how heuristic information from the problem domain can be incorporated into a formal mathematical theory of graph searching and demonstrates an optimality property of a class of search strategies.
Proceedings of the 16th International Conference on Cognitive Modeling
- S Somers
- K Mitsopoulos
- R Thomson
- C Lebiere
Advances in Neural Information Processing Systems 2
- Y Le Cun
- B Boser
- JS Denker
Proceedings of the Behavioral Representation in Modeling and Simulations (BRIMS) Conference
- BJ Best
- N Gerhart
- C Lebiere
Workshop on Bridging AI and Cognitive Science, at the 8th International Conference on Learning Representations
- K Mitsopoulos
- S Somers
- R Thomson
- C Lebiere
The Pill, Pygmy Chimps, and Degas' Horse
- C Djerassi