Search Results for author:
Found 63 papers, 20 papers with code
D-Cubed: Latent Diffusion Trajectory Optimisation for Dexterous Deformable Manipulation
In this work, we propose D-Cubed, a novel trajectory optimisation method using a latent diffusion model (LDM) trained from a task-agnostic play dataset to solve dexterous deformable object manipulation tasks.
World Models via Policy-Guided Trajectory Diffusion
Our results demonstrate that PolyGRAD outperforms state-of-the-art baselines in terms of trajectory prediction error for short trajectories, with the exception of autoregressive diffusion.
TWIST: Teacher-Student World Model Distillation for Efficient Sim-to-Real Transfer
The teacher world model then supervises a student world model that takes the domain-randomised image observations as input.
Gromov-Hausdorff Distances for Comparing Product Manifolds of Model Spaces
Recent studies propose enhancing machine learning models by aligning the geometric characteristics of the latent space with the underlying data structure.
AutoGraph: Predicting Lane Graphs from Traffic Observations
To overcome this limitation, we propose to use the motion patterns of traffic participants as lane graph annotations.
Reward-Free Curricula for Training Robust World Models
We consider robustness in terms of minimax regret over all environment instantiations and show that the minimax regret can be connected to minimising the maximum error in the world model across environment instances.
You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Example
In this work, we present a method for achieving category-level pose estimation by inspection of just a single object from a desired category.
Projections of Model Spaces for Latent Graph Inference
Graph Neural Networks leverage the connectivity structure of graphs as an inductive bias.
Efficient Skill Acquisition for Complex Manipulation Tasks in Obstructed Environments
In this work, we propose a system for efficient skill acquisition that leverages an object-centric generative model (OCGM) for versatile goal identification to specify a goal for MP combined with RL to solve complex manipulation tasks in obstructed environments.
Leveraging Scene Embeddings for Gradient-Based Motion Planning in Latent Space
Motion planning framed as optimisation in structured latent spaces has recently emerged as competitive with traditional methods in terms of planning success while significantly outperforming them in terms of computational speed.
DITTO: Offline Imitation Learning with World Models
We propose DITTO, an offline imitation learning algorithm which uses world models and on-policy reinforcement learning to addresses the problem of covariate shift, without access to an oracle or any additional online interactions.
Reaching Through Latent Space: From Joint Statistics to Path Planning in Manipulation
We present a novel approach to path planning for robotic manipulators, in which paths are produced via iterative optimisation in the latent space of a generative model of robot poses.
Variational Causal Dynamics: Discovering Modular World Models from Interventions
In doing so, VCD significantly extends the capabilities of the current state-of-the-art in latent world models while also comparing favourably in terms of prediction accuracy.
ObPose: Leveraging Pose for Object-Centric Scene Inference and Generation in 3D
We present ObPose, an unsupervised object-centric inference and generation model which learns 3D-structured latent representations from RGB-D scenes.
VAE-Loco: Versatile Quadruped Locomotion by Learning a Disentangled Gait Representation
We evaluate our approach on two versions of the real ANYmal quadruped robots and demonstrate that our method achieves a continuous blend of dynamic trot styles whilst being robust and reactive to external perturbations.
Zero-Shot Category-Level Object Pose Estimation
Object pose estimation is an important component of most vision pipelines for embodied agents, as well as in 3D vision more generally.
Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning
Key to these fields is the use of information asymmetry across architectural modules to bias which skills are learnt.
Next Steps: Learning a Disentangled Gait Representation for Versatile Quadruped Locomotion
This encourages disentanglement such that application of a drive signal to a single dimension of the latent state induces holistic plans synthesising a continuous variety of trot styles.
Semantically Grounded Object Matching for Robust Robotic Scene Rearrangement
Object rearrangement has recently emerged as a key competency in robot manipulation, with practical solutions generally involving object detection, recognition, grasping and high-level planning.
From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence
Machine learning has long since become a keystone technology, accelerating science and applications in a broad range of domains.
Universal Approximation of Functions on Sets
We provide a theoretical analysis of Deep Sets which shows that this universal approximation property is only guaranteed if the model's latent space is sufficiently high-dimensional.
E(n) Equivariant Normalizing Flows
This paper introduces a generative model equivariant to Euclidean symmetries: E(n) Equivariant Normalizing Flows (E-NFs).
GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement
Moreover, object representations are often inferred using RNNs which do not scale well to large images or iterative refinement which avoids imposing an unnatural ordering on objects in an image but requires the a priori initialisation of a fixed number of object representations.
Introspective Visuomotor Control: Exploiting Uncertainty in Deep Visuomotor Control for Failure Recovery
To recover from high uncertainty cases, the robot monitors its uncertainty along a trajectory and explores possible actions in the state-action space to bring itself to a more certain state.
Iterative SE(3)-Transformers
Motivated by this application, we implement an iterative version of the SE(3)-Transformer, an SE(3)-equivariant attention-based model for graph data.
There and Back Again: Learning to Simulate Radar Data for Real-World Applications
Here we propose to learn a radar sensor model capable of synthesising faithful radar observations based on simulated elevation maps.
Reconstruction Bottlenecks in Object-Centric Generative Models
A range of methods with suitable inductive biases exist to learn interpretable object-centric representations of images without supervision.
First Steps: Latent-Space Control with Semantic Constraints for Quadruped Locomotion
In addition, kinodynamic constraints are often non-differentiable and difficult to implement in an optimisation approach.
RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
We present RELATE, a model that learns to generate physically plausible scenes and videos of multiple interacting objects.
Goal-Conditioned End-to-End Visuomotor Control for Versatile Skill Primitives
Visuomotor control (VMC) is an effective means of achieving basic manipulation tasks such as pushing or pick-and-place from raw images.
Localising Faster: Efficient and precise lidar-based robot localisation in large-scale environments
More importantly, the Gaussian method (i. e. deep probabilistic localisation) and non-Gaussian method (i. e. MCL) can be integrated naturally via importance sampling.
Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar
This paper presents a self-supervised framework for learning to detect robust keypoints for odometry estimation and metric localisation in radar.
Improving End-to-End Object Tracking Using Relational Reasoning
Relational reasoning, the ability to model interactions and relations between objects, is valuable for robust multi-object tracking and pivotal for trajectory prediction.
Attention-Privileged Reinforcement Learning
Image-based Reinforcement Learning is known to suffer from poor sample efficiency and generalisation to unseen visuals such as distractors (task-independent aspects of the observation space).
Imagine That! Leveraging Emergent Affordances for 3D Tool Synthesis
In this paper we explore the richness of information captured by the latent space of a vision-based generative model.
Imagine That! Leveraging Emergent Affordances for Tool Synthesis in Reaching Tasks
In this paper we investigate an artificial agent's ability to perform task-focused tool synthesis via imagination.
Attention Privileged Reinforcement Learning for Domain Transfer
Applying reinforcement learning (RL) to physical systems presents notable challenges, given requirements regarding sample efficiency, safety, and physical constraints compared to simulated environments.
Masking by Moving: Learning Distraction-Free Radar Odometry from Pose Information
This paper presents an end-to-end radar odometry system which delivers robust, real-time pose estimates based on a learned embedding space free of sensing artefacts and distractor objects.
The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset
In this paper we present The Oxford Radar RobotCar Dataset, a new dataset for researching scene understanding using Millimetre-Wave FMCW scanning radar data.
Robotics Signal Processing
GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning.
Ranked #1 on
Image Generation
on Multi-dSprites
End-to-end Recurrent Multi-Object Tracking and Trajectory Prediction with Relational Reasoning
The majority of contemporary object-tracking approaches do not model interactions between objects.
Guiding Physical Intuition with Neural Stethoscopes
Using an adversarial stethoscope, the network is successfully de-biased, leading to a performance increase from 66% to 88%.
On the Limitations of Representing Functions on Sets
Recent work on the representation of functions on sets has considered the use of summation in a latent space to enforce permutation invariance.
Dropout Distillation for Efficiently Estimating Model Confidence
We also propose better calibration within the state of the art Faster R-CNN object detection framework and show, using the COCO dataset, that DDN helps train better calibrated object detectors.
Scrutinizing and De-Biasing Intuitive Physics with Neural Stethoscopes
Conversely, training on an easy dataset where visual cues are positively correlated with stability, the baseline model learns a bias leading to poor performance on a harder dataset.
Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects
It can reliably discover and track objects throughout the sequence of frames, and can also generate future frames conditioning on the current frame, thereby simulating expected motion of objects.
ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking
Physical intuition is pivotal for intelligent agents to perform complex tasks.
TACO: Learning Task Decomposition via Temporal Alignment for Control
Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks.
Incremental Adversarial Domain Adaptation for Continually Changing Environments
Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models.
Generative Adversarial Network
Unsupervised Domain Adaptation
Driven to Distraction: Self-Supervised Distractor Learning for Robust Monocular Visual Odometry in Urban Environments
We present a self-supervised approach to ignoring "distractors" in camera images for the purposes of robustly estimating vehicle motion in cluttered urban environments.
What Makes a Place? Building Bespoke Place Dependent Object Detectors for Robotics
This paper is about enabling robots to improve their perceptual performance through repeated use in their operating environment, creating local expert detectors fitted to the places through which a robot moves.
Mutual Alignment Transfer Learning
Training robots for operation in the real world is a complex, time consuming and potentially expensive task.
Hierarchical Attentive Recurrent Tracking
Class-agnostic object tracking is particularly difficult in cluttered environments as target specific discriminative models cannot be learned a priori.
Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation
Appearance changes due to weather and seasonal conditions represent a strong impediment to the robust implementation of machine learning systems in outdoor robotics.
Incorporating Human Domain Knowledge into Large Scale Cost Function Learning
Recent advances have shown the capability of Fully Convolutional Neural Networks (FCN) to model cost functions for motion planning in the context of learning driving preferences purely based on demonstration data from human drivers.
Find Your Own Way: Weakly-Supervised Segmentation of Path Proposals for Urban Autonomy
We present a weakly-supervised approach to segmenting proposed drivable paths in images with the goal of autonomous driving in complex urban environments.
Deep Tracking on the Move: Learning to Track the World from a Moving Vehicle using Recurrent Neural Networks
This paper presents an end-to-end approach for tracking static and dynamic objects for an autonomous vehicle driving through crowded urban environments.
Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks
This paper proposes a computationally efficient approach to detecting objects natively in 3D point clouds using convolutional neural networks (CNNs).
Ranked #1 on
Object Detection
on KITTI Cyclists Hard
Watch This: Scalable Cost-Function Learning for Path Planning in Urban Environments
In this work, we present an approach to learn cost maps for driving in complex urban environments from a very large number of demonstrations of driving behaviour by human experts.
End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks
In this work we present a novel end-to-end framework for tracking and classifying a robot's surroundings in complex, dynamic and only partially observable real-world environments.
Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks
This paper presents to the best of our knowledge the first end-to-end object tracking approach which directly maps from raw sensor input to object tracks in sensor space without requiring any feature engineering or system identification in the form of plant or sensor models.
Maximum Entropy Deep Inverse Reinforcement Learning
This paper presents a general framework for exploiting the representational capacity of neural networks to approximate complex, nonlinear reward functions in the context of solving the inverse reinforcement learning (IRL) problem.
Modelling Observation Correlations for Active Exploration and Robust Object Detection
In particular, the performance of detection algorithms is commonly sensitive to the position of the sensor relative to the objects in the scene.
