Search for: All records

In the face of difficult exploration problems in reinforcement learning, we study whether giving an agent an object-centric mapping (describing a set of items and their attributes) allow for more efficient learning. We found this problem is best solved hierarchically by modelling items at a higher level of state abstraction to pixels, and attribute change at a higher level of temporal abstraction to primitive actions. This abstraction simplifies the transition dynamic by making specific future states easier to predict. We make use of this to propose a fully model-based algorithm that learns a discriminative world model, plans to explore efficiently with only a count-based intrinsic reward, and can subsequently plan to reach any discovered (abstract) states. We demonstrate the model's ability to (i) efficiently solve single tasks, (ii) transfer zero-shot and few-shot across item types and environments, and (iii) plan across long horizons. Across a suite of 2D crafting and MiniHack environments, we empirically show our model significantly out-performs state-of-the-art low-level methods (without abstraction), as well as performant model-free and model-based methods using the same abstraction. Finally, we show how to learn low level object-perturbing policies via reinforcement learning, and the object mapping itself by supervised learning. 

In recent years, aiming to enhance and extend user experiences beyond the real world, Extended Reality (XR) has emerged to become a new paradigm that enables a plethora of applications [1], e.g., online gaming, online conferencing, social media, etc. XR refers to the human-machine interactions that combine real and virtual environments with the support of computing/communications technologies and wearable devices. The XR content is generated by providers or other users, including audio, video and other metadata. In general, the generated XR content is transmitted to XR devices and rendered into XR scenes (i.e., to generate an image from a 2D or 3D model by means of a computer program), where users can experience a hybrid experience of the real and virtual worlds. 

We propose using surface and aerial shared autonomous electric vehicles (SAEVs) to improve the resilience of infrastructure and communities, or SAEV-R. In disruptive events, SAEVs can be temporarily deployed to evacuate and rescue at-risk populations, provide essential supplies and services to vulnerable households, and transport repair crews and equipment. We present a modeling framework for feasibility analysis and strategic planning associated with deploying SAEVs for disaster relief. The framework guides our examination of three scenarios: a hurricane-induced power outage, a pandemic-affected vulnerable population, and earthquake-damaged infrastructure. The results demonstrate the flexibility of the proposed framework and showcase the potential and versatility of SAEV-R systems to improve resilience. 

The prevalent point cloud compression (PCC) standards of today are utilized to encode various types of point cloud data, allowing for reasonable bandwidth and storage usage. With increasing demand for high-fidelity three-dimensional (3D) models for a large variety of applications, including immersive visual communication, Augmented reality (AR) and Virtual Reality (VR), navigation, autonomous driving, and smart city, point clouds are seeing increasing usage and development to meet the increasing demands. However, with the advancements in 3D modelling and sensing, the amount of data required to accurately depict such representations and models is likewise ballooning to increasingly large proportions, leading to the development and standardization of the point cloud compression standards. In this article, we provide an overview of some topical and popular MPEG point cloud compression (PCC) standards. We discuss the development and applications of the Geometry-based PCC (G-PCC) and Video-based PCC (V-PCC) standards as they escalate in importance in an era of virtual reality and machine learning. Finally, we conclude our article describing the future research directions and applications of the PCC standards of today.