Breakthroughs in machine learning in the last decade have led to `digital intelligence', i.e. machine learning models capable of learning from vast amounts of labeled data to perform several digital tasks such as speech recognition, face recognition, machine translation and so on. The goal of this thesis is to make progress towards designing algorithms capable of `physical intelligence', i.e. building intelligent autonomous navigation agents capable of learning to perform complex navigation tasks in the physical world involving visual perception, natural language understanding, reasoning, planning, and sequential decision making. Despite several advances in classical navigation methods in the last few decades, current navigation agents struggle at long-term semantic navigation tasks. In the first part of the thesis, we discuss our work on short-term navigation using end-to-end reinforcement learning to tackle challenges such as obstacle avoidance, semantic perception, language grounding, and reasoning. In the second part, we present a new class of navigation methods based on modular learning and structured explicit map representations, which leverage the strengths of both classical and end-to-end learning methods, to tackle long-term navigation tasks. We show that these methods are able to effectively tackle challenges such as localization, mapping, long-term planning, exploration and learning semantic priors. These modular learning methods are capable of long-term spatial and semantic understanding and achieve state-of-the-art results on various navigation tasks.

You work with a computer simulation technique called agent-based computational models. Could you explain how these work? How do you create artificial societies using this technique? In principle, the research path is straightforward. First, I identify some macroscopic patterns that I want to explain, say educational inequalities across socio-economic groups.

This paper explores the use of factor graphs as an inference and analysis tool for Bayesian peer-to-peer decentralized data fusion. We propose a framework by which agents can each use local factor graphs to represent relevant partitions of a complex global joint probability distribution, thus allowing them to avoid reasoning over the entirety of a more complex model and saving communication as well as computation cost. This allows heterogeneous multi-robot systems to cooperate on a variety of real world, task oriented missions, where scalability and modularity are key. To develop the initial theory and analyze the limits of this approach, we focus our attention on static linear Gaussian systems in tree-structured networks and use Channel Filters (also represented by factor graphs) to explicitly track common information. We discuss how this representation can be used to describe various multi-robot applications and to design and analyze new heterogeneous data fusion algorithms. We validate our method in simulations of a multi-agent multi-target tracking and cooperative multi-agent mapping problems, and discuss the computation and communication gains of this approach.

The significant increase in the number of individuals with chronic ailments (including the elderly and disabled) has dictated an urgent need for an innovative model for healthcare systems. The evolved model will be more personalized and less reliant on traditional brick-and-mortar healthcare institutions such as hospitals, nursing homes, and long-term healthcare centers. The smart healthcare system is a topic of recently growing interest and has become increasingly required due to major developments in modern technologies, especially in artificial intelligence (AI) and machine learning (ML). This paper is aimed to discuss the current state-of-the-art smart healthcare systems highlighting major areas like wearable and smartphone devices for health monitoring, machine learning for disease diagnosis, and the assistive frameworks, including social robots developed for the ambient assisted living environment. Additionally, the paper demonstrates software integration architectures that are very significant to create smart healthcare systems, integrating seamlessly the benefit of data analytics and other tools of AI. The explained developed systems focus on several facets: the contribution of each developed framework, the detailed working procedure, the performance as outcomes, and the comparative merits and limitations. The current research challenges with potential future directions are addressed to highlight the drawbacks of existing systems and the possible methods to introduce novel frameworks, respectively. This review aims at providing comprehensive insights into the recent developments of smart healthcare systems to equip experts to contribute to the field.

Do you ever wonder what goes behind bringing various levels of autonomy to vehicles? What the vehicle sees (perception) and how the vehicle predicts the actions of different agents in the scene (behavior prediction) are the first two steps in autonomous systems. In order for these steps to be successful, large-scale driving datasets are key. Driving datasets typically comprise of data captured using multiple sensors such as cameras, LIDARs, radars, and GPS, in a variety of traffic scenarios during different times of the day under varied weather conditions and locations. The Amazon Machine Learning Solutions Lab is collaborating with the Laboratory of Intelligent and Safe Automobiles (LISA Lab) at the University of California, San Diego (UCSD) to build a large, richly annotated, real-world driving dataset with fine-grained vehicle, pedestrian, and scene attributes. This post describes the dataset label taxonomy and labeling architecture for 2D bounding boxes using Amazon SageMaker Ground Truth. Ground Truth is a fully managed data labeling service that makes it easy to build highly accurate training datasets for machine learning (ML) workflows. These workflows support a variety of use cases, including 3D point clouds, video, images, and text.

An increasingly common setting in machine learning involves multiple parties, each with their own data, who want to jointly make predictions on future test points. Agents wish to benefit from the collective expertise of the full set of agents to make better predictions than they would individually, but may not be willing to release their data or model parameters. In this work, we explore a decentralized mechanism to make collective predictions at test time, leveraging each agent's pre-trained model without relying on external validation, model retraining, or data pooling. Our approach takes inspiration from the literature in social science on human consensus-making. We analyze our mechanism theoretically, showing that it converges to inverse meansquared-error (MSE) weighting in the large-sample limit. To compute error bars on the collective predictions we propose a decentralized Jackknife procedure that evaluates the sensitivity of our mechanism to a single agent's prediction. Empirically, we demonstrate that our scheme effectively combines models with differing quality across the input space. The proposed consensus prediction achieves significant gains over classical model averaging, and even outperforms weighted averaging schemes that have access to additional validation data.

Automated customer service agents became the top Artificial Intelligence (AI) use case for the Indian organisations in 2020 as the Covid-19 pandemic kept millions at home and face-to-face interactions diminished across industries. The AI use cases gained momentum in India, driven by the need to ensure speed of new product development, facilitate better customer experience, improve higher employee productivity, and achieve high competitiveness in the market. For 2020, automated customer service agent is the top AI use case and it is also witnessing other use cases like fraud analysis and investigation, IT automation, recommendation system, and diagnosis and treatment gain momentum. Indian organisations are leveraging AI to help them with real-time analysis, providing enhanced experiences and automation. With AI that supports innovations at scale, delivers enhanced customer experience and improves operational efficiency, organisations will continue to find ways to gain more value from their data and improve overall customer experience, the report showed.

Standard Epistemic Logic (EL) mainly studies reasoning patterns of knowing that ϕ, despite early contributions by Hintikka on formulating other know-wh expressions such as knowing who and why using first-order and higher-order modal logic. In recent years, there is a resurgence of interest on epistemic logics of know-wh powered by the new techniques for fragments of firstorder modal logic based on the so-called bundle modalities packing a quantifier and a normal epistemic modality together [26, 24, 21]. Within the varieties of logics of know-wh, the logics of know-how received the most attention in AI (cf.

Rethinking cities is now more imperative than ever, as society faces global challenges such as population growth and climate change. The design of cities can not be abstracted from the design of its mobility system, and, therefore, efficient solutions must be found to transport people and goods throughout the city in an ecological way. An autonomous bicycle-sharing system would combine the most relevant benefits of vehicle sharing, electrification, autonomy, and micro-mobility, increasing the efficiency and convenience of bicycle-sharing systems and incentivizing more people to bike and enjoy their cities in an environmentally friendly way. Due to the uniqueness and radical novelty of introducing autonomous driving technology into bicycle-sharing systems and the inherent complexity of these systems, there is a need to quantify the potential impact of autonomy on fleet performance and user experience. This paper presents an ad-hoc agent-based simulator that provides an in-depth understanding of the fleet behavior of autonomous bicycle-sharing systems in realistic scenarios, including a rebalancing system based on demand prediction. In addition, this work describes the impact of different parameters on system efficiency and service quality and quantifies the extent to which an autonomous system would outperform current bicycle-sharing schemes. The obtained results show that with a fleet size three and a half times smaller than a station-based system and eight times smaller than a dockless system, an autonomous system can provide overall improved performance and user experience even with no rebalancing. These findings indicate that the remarkable efficiency of an autonomous bicycle-sharing system could compensate for the additional cost of autonomous bicycles.

We investigate Kantian equilibria in finite normal form games, a class of non-Nashian, morally motivated courses of action that was recently proposed in the economics literature. We highlight a number of problems with such equilibria, including computational intractability, a high price of miscoordination, and problematic extension to general normal form games. We give such a generalization based on concept of program equilibria, and point out that that a practically relevant generalization may not exist. To remedy this we propose some general, intuitive, computationally tractable, other-regarding equilibria that are special cases Kantian equilibria, as well as a class of courses of action that interpolates between purely self-regarding and Kantian behavior.