A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Improves AI agents' 3D navigation by learning from failures and 3D spatial relationships.
3D shape instantiation which reconstructs the 3D shape of a target from limited 2D images or projections is an emerging technique for surgical intervention. It improves the currently less-informative and insufficient 2D navigation schemes for robot-assisted Minimally Invasive Surgery (MIS) to 3D navigation. Previously,…
The ability to use a 2D map to navigate a complex 3D environment is quite remarkable, and even difficult for many humans. Localization and navigation is also an important problem in domains such as robotics, and has recently become a focus of the deep reinforcement learning community. In this paper we teach a reinforce…
The problem of pursuing a moving target is always one of the main topics in navigation. In the literatures, there are two well-known algorithms called Pure Pursuit and Pure Rendezvous navigation in the 3-dimensional space . In this paper, these two methods are combined to introduce a novel family of pursu…
Agent learns to navigate uncertain 3D maps using a hybrid planner.
New framework for 3D spatial topology enumeration and identification.
Most common navigation tasks in human environments require auxiliary arm interactions, e.g. opening doors, pressing buttons and pushing obstacles away. This type of navigation tasks, which we call Interactive Navigation, requires the use of mobile manipulators: mobile bases with manipulation capabilities. Interactive N…
3D object detection improved using energy-based models.
Accurate volume segmentation from the Computed Tomography (CT) scan is a common prerequisite for pre-operative planning, intra-operative guidance and quantitative assessment of therapeutic outcomes in robot-assisted Minimally Invasive Surgery (MIS). 3D Deep Convolutional Neural Network (DCNN) is a viable solution for t…
We introduce a variational approach to learning and inference of temporally hierarchical structure and representation for sequential data. We propose the Variational Temporal Abstraction (VTA), a hierarchical recurrent state space model that can infer the latent temporal structure and thus perform the stochastic state …
Worldsheet wraps a 3D mesh sheet onto a single image to synthesize novel views.
New meta-RL method avoids exploration-exploitation trade-off.
Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and embodied question answering. In this paper, we propose a multitask model capable of jointly learnin…
WILD-SCAV benchmarks AI in complex 3D FPS environments.
Depth perception is a key component for autonomous systems that interact in the real world, such as delivery robots, warehouse robots, and self-driving cars. Tasks in autonomous robotics such as 3D object recognition, simultaneous localization and mapping (SLAM), path planning and navigation, require some form of 3D sp…
We consider the exploration problem: an agent equipped with a depth sensor must map out a previously unknown environment using as few sensor measurements as possible. We propose an approach based on supervised learning of a greedy algorithm. We provide a bound on the optimality of the greedy algorithm using submodulari…
Smart and agile drones are fast becoming ubiquitous at the edge of the cloud. The usage of these drones are constrained by their limited power and compute capability. In this paper, we present a Transfer Learning (TL) based approach to reduce on-board computation required to train a deep neural network for autonomous n…
Deep learning is attracting significant interest in the neuroimaging community as a means to diagnose psychiatric and neurological disorders from structural magnetic resonance images. However, there is a tendency amongst researchers to adopt architectures optimized for traditional computer vision tasks, rather than des…
Flatland is a simple, lightweight environment for fast prototyping and testing of reinforcement learning agents. It is of lower complexity compared to similar 3D platforms (e.g. DeepMind Lab or VizDoom), but emulates physical properties of the real world, such as continuity, multi-modal partially-observable states with…
The reconstruction of an object's shape or surface from a set of 3D points plays an important role in medical image analysis, e.g. in anatomy reconstruction from tomographic measurements or in the process of aligning intra-operative navigation and preoperative planning data. In such scenarios, one usually has to deal w…
Modern reinforcement learning algorithms reach super-human performance on many board and video games, but they are sample inefficient, i.e. they typically require significantly more playing experience than humans to reach an equal performance level. To improve sample efficiency, an agent may build a model of the enviro…
Introduces a natural parallel translation for navigation data.
Learning in sparse reward settings remains a challenge in Reinforcement Learning, which is often addressed by using intrinsic rewards. One promising strategy is inspired by human curiosity, requiring the agent to learn to predict the future. In this paper a curiosity-driven agent is extended to use these predictions di…
Challenge to separate Earth's magnetic field from vehicle's magnetic field for accurate navigation.
Navigation in Lorentz Finsler geometry induces isoparametric hypersurfaces.
The paper solves navigation problems on conic Kropina manifolds and establishes curvature relationships.
Robotic navigation improves with RL and ultrasound images.
Improved robot navigation using multi-head attention for natural language instructions.
Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and high-dimensionality of sensorimotor spaces which are inherent in such problems. We present a nov…
SLAM-net learns to navigate visually in challenging indoor environments.
Entropy regularization is used to get improved optimization performance in reinforcement learning tasks. A common form of regularization is to maximize policy entropy to avoid premature convergence and lead to more stochastic policies for exploration through action space. However, this does not ensure exploration in th…
Bayesian model for energy consumption helps electric vehicles navigate efficiently.
This work analyzes minimum-time navigation on Riemannian manifolds using Finsler geometry.
Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this challenge in the context of man-made environments, which are visually diverse but contain intrinsic semantic regularities. We propose a hybrid …
Deep learning agent improves pedestrian navigation in urban environments.
We introduce a conceptually simple and scalable framework for continual learning domains where tasks are learned sequentially. Our method is constant in the number of parameters and is designed to preserve performance on previously encountered tasks while accelerating learning progress on subsequent problems. This is a…
Bayesian model for energy-efficient EV navigation.
Solves time-minimizing navigation on a mountain slope using Riemann-Finsler geometry.
Value Iteration Networks (VINs) are effective differentiable path planning modules that can be used by agents to perform navigation while still maintaining end-to-end differentiability of the entire architecture. Despite their effectiveness, they suffer from several disadvantages including training instability, random …
Many mobile robots rely on 2D laser scanners for localization, mapping, and navigation. However, those sensors are unable to correctly provide distance to obstacles such as glass panels and tables whose actual occupancy is invisible at the height the sensor is measuring. In this work, instead of estimating the distance…
Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning architecture capable of navigating an agent, e.g. a mobile robot, to a target giv…
The paper develops a method to learn navigation costs from expert demonstrations in partially observable environments.
New algorithms solve time-dependent navigation problems, including zig-zag paths.
VALAN is a lightweight and scalable software framework for deep reinforcement learning based on the SEED RL architecture. The framework facilitates the development and evaluation of embodied agents for solving grounded language understanding tasks, such as Vision-and-Language Navigation and Vision-and-Dialog Navigation…
In this paper we propose a novel accurate method for dead-reckoning of wheeled vehicles based only on an Inertial Measurement Unit (IMU). In the context of intelligent vehicles, robust and accurate dead-reckoning based on the IMU may prove useful to correlate feeds from imaging sensors, to safely navigate through obstr…
OtoWorld helps agents learn to navigate by listening in interactive environments.
Paper introduces timing-based adversarial attacks on DRL-based navigation systems.
Investigates stochastic networks on disordered lattices, converging to Brownian web in 2D.