Entailment trees have been proposed to simulate the human reasoning process of explanation generation in the context of open--domain textual question answering. However, in practice, manually constructing these explanation trees proves a laborious process that requires active human involvement. Given the complexity of capturing the line of reasoning from question to the answer or from claim to premises, the issue arises of how to assist the user in efficiently constructing multi--level entailment trees given a large set of available facts. In this paper, we frame the construction of entailment trees as a sequence of active premise selection steps, i.e., for each intermediate node in an explanation tree, the expert needs to annotate positive and negative examples of premise facts from a large candidate list. We then iteratively fine--tune pre--trained Transformer models with the resulting positive and tightly controlled negative samples and aim to balance the encoding of semantic relationships and explanatory entailment relationships. Experimental evaluation confirms the measurable efficiency gains of the proposed active fine--tuning method in facilitating entailment trees construction: up to 20\% improvement in explanatory premise selection when compared against several alternatives.

An industrial connector insertion task requires submillimeter positioning and grasp pose compensation for a plug. Thus, highly accurate estimation of the relative pose between a plug and socket is fundamental for achieving the task. World models are promising technologies for visuomotor control because they obtain appropriate state representation to jointly optimize feature extraction and latent dynamics model. Recent studies show that the NewtonianVAE, a type of the world model, acquires latent space equivalent to mapping from images to physical coordinates. Proportional control can be achieved in the latent space of NewtonianVAE. However, applying NewtonianVAE to high-accuracy industrial tasks in physical environments is an open problem. Moreover, the existing framework does not consider the grasp pose compensation in the obtained latent space. In this work, we proposed tactile-sensitive NewtonianVAE and applied it to a USB connector insertion with grasp pose variation in the physical environments. We adopted a GelSight-type tactile sensor and estimated the insertion position compensated by the grasp pose of the plug. Our method trains the latent space in an end-to-end manner, and no additional engineering and annotation are required. Simple proportional control is available in the obtained latent space. Moreover, we showed that the original NewtonianVAE fails in some situations, and demonstrated that domain knowledge induction improves model accuracy. This domain knowledge can be easily obtained using robot specification and grasp pose error measurement. We demonstrated that our proposed method achieved a 100\% success rate and 0.3 mm positioning accuracy in the USB connector insertion task in the physical environment. It outperformed SOTA CNN-based two-stage goal pose regression with grasp pose compensation using coordinate transformation.

One of my favorite little bits of python is __subclasshook__. Abstract Base Classes with __subclasshook__ can define what counts as a subclass of the ABC, even if the target doesn't know about the ABC. You can do some weird stuff with this. Back in 2019 I used it to create non-monotonic types, where something counts as a NotIterable if it doesn't have the __iter__ method. There wasn't anything too diabolical you could do with this: nothing in Python really interacted with ABCs, limiting the damage you could do with production code.

Knowledge-grounded dialogue systems are challenging to build due to the lack of training data and heterogeneous knowledge sources. Existing systems perform poorly on unseen topics due to limited topics covered in the training data. In addition, heterogeneous knowledge sources make it challenging for systems to generalize to other tasks because knowledge sources in different knowledge representations require different knowledge encoders. To address these challenges, we present PLUG, a language model that homogenizes different knowledge sources to a unified knowledge representation for knowledge-grounded dialogue generation tasks. PLUG is pre-trained on a dialogue generation task conditioned on a unified essential knowledge representation. It can generalize to different downstream knowledge-grounded dialogue generation tasks with a few training examples. The empirical evaluation on two benchmarks shows that our model generalizes well across different knowledge-grounded tasks. It can achieve comparable performance with state-of-the-art methods under a fully-supervised setting and significantly outperforms other methods in zero-shot and few-shot settings.

To the right, search space, where all states with the same initial-state distance (g) and estimated goal distance (h) are represented by a single binary decision diagram (to the left), and only those whose g h solution cost need to be considered. Daniel Fišer, Álvaro Torralba and Joerg Hoffmann won an outstanding paper runners-up award at AAAI 2022 for their paper Operator-potential heuristics for symbolic search. Here, Álvaro tells us more about the field of optical planning, their methodology, and how potential heuristics can be used in symbolic search with very positive results. At a very general level, the research is on automated planning. This is a sub-area of AI where we try to answer the question: what is the best way to act given our knowledge of the world?

A hallmark of human intelligence is the ability to construct self-contained chunks of knowledge and reuse them in novel combinations for solving different problems. Learning such compositional structures has been a challenge for artificial systems, due to the underlying combinatorial search. To date, research into compositional learning has largely proceeded separately from work on lifelong or continual learning. This dissertation integrated these two lines of work to present a general-purpose framework for lifelong learning of functionally compositional structures. The framework separates the learning into two stages: learning how to combine existing components to assimilate a novel problem, and learning how to adapt the existing components to accommodate the new problem. This separation explicitly handles the trade-off between stability and flexibility. This dissertation instantiated the framework into various supervised and reinforcement learning (RL) algorithms. Supervised learning evaluations found that 1) compositional models improve lifelong learning of diverse tasks, 2) the multi-stage process permits lifelong learning of compositional knowledge, and 3) the components learned by the framework represent self-contained and reusable functions. Similar RL evaluations demonstrated that 1) algorithms under the framework accelerate the discovery of high-performing policies, and 2) these algorithms retain or improve performance on previously learned tasks. The dissertation extended one lifelong compositional RL algorithm to the nonstationary setting, where the task distribution varies over time, and found that modularity permits individually tracking changes to different elements in the environment. The final contribution of this dissertation was a new benchmark for compositional RL, which exposed that existing methods struggle to discover the compositional properties of the environment.

Reliable navigation systems have a wide range of applications in robotics and autonomous driving. Current approaches employ an open-loop process that converts sensor inputs directly into actions. However, these open-loop schemes are challenging to handle complex and dynamic real-world scenarios due to their poor generalization. Imitating human navigation, we add a reasoning process to convert actions back to internal latent states, forming a two-stage closed loop of perception, decision-making, and reasoning. Firstly, VAE-Enhanced Demonstration Learning endows the model with the understanding of basic navigation rules. Then, two dual processes in RL-Enhanced Interaction Learning generate reward feedback for each other and collectively enhance obstacle avoidance capability. The reasoning model can substantially promote generalization and robustness, and facilitate the deployment of the algorithm to real-world robots without elaborate transfers. Experiments show our method is more adaptable to novel scenarios compared with state-of-the-art approaches.

This work proposes a taxonomy for diagnosis computation methods which allows their standardized assessment, classification and comparison. The aim is to (i) give researchers and practitioners an impression of the diverse landscape of available diagnostic techniques, (ii) allow them to easily retrieve the main features as well as pros and cons of the approaches, (iii) enable an easy and clear comparison of the techniques based on their characteristics wrt. a list of important and well-defined properties, and (iv) facilitate the selection of the "right" algorithm to adopt for a particular problem case, e.g., in practical diagnostic settings, for comparison in experimental evaluations, or for reuse, modification, extension, or improvement in the course of research.

Long-term autonomy of robotic systems implicitly requires dependable platforms that are able to naturally handle hardware and software faults, problems in behaviors, or lack of knowledge. Model-based dependable platforms additionally require the application of rigorous methodologies during the system development, including the use of correct-by-construction techniques to implement robot behaviors. As the level of autonomy in robots increases, so do the cost of offering guarantees about the dependability of the system. Certifiable dependability of autonomous robots, we argue, can benefit from formal models of the integration of several cognitive functions, knowledge processing, reasoning, and meta-reasoning. Here we put forward the case for a generative model of cognitive architectures for autonomous robotic agents that subscribes to the principles of model-based engineering and certifiable dependability, autonomic computing, and knowledge-enabled robotics.

Through generations, the field of artificial intelligence has persevered and become a hugely significant part of modern life. Of the myriad technological advances of the 20th and 21st centuries, one of the most influential is undoubtedly artificial intelligence (AI). From search engine algorithms reinventing how we look for information to Amazon's Alexa in the consumer sector, AI has become a major technology driving the entire tech industry forward into the future. According to a study from Grand View Research, the global AI industry was valued at $93.5 billion in 2021. AI as a force in the tech industry exploded in prominence in the 2000s and 2010s, but AI has been around in some form or fashion since at least 1950 and arguably stretches back even further than that.