Search Results for author:
Found 12 papers, 7 papers with code
DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors
In this paper, we present theDeepMind Control Visual Benchmark (DMC-VB), a dataset collected in the DeepMind Control Suite to evaluate the robustness of offline RL agents for solving continuous control tasks from visual input in the presence of visual distractors.
A Touch, Vision, and Language Dataset for Multimodal Alignment
This is partially due to the difficulty of obtaining natural language labels for tactile data and the complexity of aligning tactile readings with both visual observations and language descriptions.
Neural feels with neural fields: Visuo-tactile perception for in-hand manipulation
Our neural representation driven by multimodal sensing can serve as a perception backbone towards advancing robot dexterity.
Decentralization and Acceleration Enables Large-Scale Bundle Adjustment
In this paper, we present a fully decentralized method that alleviates computation and communication bottlenecks to solve arbitrarily large bundle adjustment problems.
Theseus: A Library for Differentiable Nonlinear Optimization
We present Theseus, an efficient application-agnostic open source library for differentiable nonlinear least squares (DNLS) optimization built on PyTorch, providing a common framework for end-to-end structured learning in robotics and vision.
iSDF: Real-Time Neural Signed Distance Fields for Robot Perception
We present iSDF, a continual learning system for real-time signed distance field (SDF) reconstruction.
A Robot Web for Distributed Many-Device Localisation
We show that a distributed network of robots or other devices which make measurements of each other can collaborate to globally localise via efficient ad-hoc peer to peer communication.
Incremental Abstraction in Distributed Probabilistic SLAM Graphs
Scene graphs represent the key components of a scene in a compact and semantically rich way, but are difficult to build during incremental SLAM operation because of the challenges of robustly identifying abstract scene elements and optimising continually changing, complex graphs.
A visual introduction to Gaussian Belief Propagation
In this article, we present a visual introduction to Gaussian Belief Propagation (GBP), an approximate probabilistic inference algorithm that operates by passing messages between the nodes of arbitrarily structured factor graphs.
iMAP: Implicit Mapping and Positioning in Real-Time
We show for the first time that a multilayer perceptron (MLP) can serve as the only scene representation in a real-time SLAM system for a handheld RGB-D camera.
Bundle Adjustment on a Graph Processor
Graph processors such as Graphcore's Intelligence Processing Unit (IPU) are part of the major new wave of novel computer architecture for AI, and have a general design with massively parallel computation, distributed on-chip memory and very high inter-core communication bandwidth which allows breakthrough performance for message passing algorithms on arbitrary graphs.
FutureMapping 2: Gaussian Belief Propagation for Spatial AI
We argue the case for Gaussian Belief Propagation (GBP) as a strong algorithmic framework for the distributed, generic and incremental probabilistic estimation we need in Spatial AI as we aim at high performance smart robots and devices which operate within the constraints of real products.
