Search Results for author:
Found 70 papers, 18 papers with code
Simple Online and Realtime Tracking
This paper explores a pragmatic approach to multiple object tracking where the main focus is to associate objects efficiently for online and realtime applications.
Ranked #2 on
Multi-Object Tracking
on MOT15
Expected Similarity Estimation for Large-Scale Batch and Streaming Anomaly Detection
We present a novel algorithm for anomaly detection on very large datasets and data streams.
Multi-Objective Bayesian Optimisation and Joint Inversion for Active Sensor Fusion
A critical decision process in data acquisition for mineral and energy resource exploration is how to efficiently combine a variety of sensor types and to minimize total cost.
BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGym
This paper outlines BayesSimIG: a library that provides an implementation of BayesSim integrated with the recently released NVIDIA IsaacGym.
A User's Guide to Calibrating Robotics Simulators
Simulators are a critical component of modern robotics research.
Online Domain Adaptation for Occupancy Mapping
Further, with the use of high-fidelity driving simulators and real-world datasets, we demonstrate how parameters of 2D and 3D occupancy maps can be automatically adapted to accord with local spatial changes.
BORE: Bayesian Optimization by Density-Ratio Estimation
Bayesian optimization (BO) is among the most effective and widely-used blackbox optimization methods.
BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators
We introduce BayesSim, a framework for robotics simulations allowing a full Bayesian treatment for the parameters of the simulator.
Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems
The complex motions are encoded as rollouts of a stable dynamical system, which, under a change of coordinates defined by a diffeomorphism, is equivalent to a simple, hand-specified dynamical system.
Hyperparameter Learning for Conditional Kernel Mean Embeddings with Rademacher Complexity Bounds
Conditional kernel mean embeddings are nonparametric models that encode conditional expectations in a reproducing kernel Hilbert space.
Learning to Plan Hierarchically from Curriculum
Our framework decomposes transition dynamics into skill effects and success conditions, which allows fast planning by reasoning on effects, while learning conditions from interactions with the world.
DISCO: Double Likelihood-free Inference Stochastic Control
Accurate simulation of complex physical systems enables the development, testing, and certification of control strategies before they are deployed into the real systems.
Batch Bayesian optimisation via density-ratio estimation with guarantees
Bayesian optimisation (BO) algorithms have shown remarkable success in applications involving expensive black-box functions.
Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference
We formalize the problem of learning interdomain correspondences in the absence of paired data as Bayesian inference in a latent variable model (LVM), where one seeks the underlying hidden representations of entities from one domain as entities from the other domain.
Index Set Fourier Series Features for Approximating Multi-dimensional Periodic Kernels
Periodicity is often studied in timeseries modelling with autoregressive methods but is less popular in the kernel literature, particularly for higher dimensional problems such as in textures, crystallography, and quantum mechanics.
Learning Non-Stationary Space-Time Models for Environmental Monitoring
One of the primary aspects of sustainable development involves accurate understanding and modeling of environmental phenomena.
Adaptive Sensing for Learning Nonstationary Environment Models
The core idea in LISAL is to learn two models using Gaussian processes (GPs) wherein the first is a nonstationary GP directly modeling the phenomenon.
Correcting differences in multi-site neuroimaging data using Generative Adversarial Networks
Here we transform T1-weighted brain images collected from two different sites into MR images from the same site.
Learning to Race through Coordinate Descent Bayesian Optimisation
On the other hand, the cost to evaluate the policy's performance might also be high, being desirable that a solution can be found with as few interactions as possible with the real system.
Bayesian Optimisation for Safe Navigation under Localisation Uncertainty
In outdoor environments, mobile robots are required to navigate through terrain with varying characteristics, some of which might significantly affect the integrity of the platform.
Urban Scene Segmentation with Laser-Constrained CRFs
The proposed method is evaluated on images and 3D point cloud data gathered in urban environments where image data provides the appearance features needed by the CRF, while the 3D point cloud data provides global spatial constraints over sets of nodes.
Online Adaptation of Deep Architectures with Reinforcement Learning
As more data is collected sequentially, quickly adapting to changes in the data distribution can offer several competitive advantages such as avoiding loss of prior knowledge and more efficient learning.
Transductive Learning for Multi-Task Copula Processes
We tackle the problem of multi-task learning with copula process.
Integer Programming Relaxations for Integrated Clustering and Outlier Detection
We present and contrast three relaxations to the integer program formulation: (i) a linear programming formulation (LP) (ii) an extension of affinity propagation to outlier detection (APOC) and (iii) a Lagrangian duality based formulation (LD).
Egocentric Activity Recognition on a Budget
Recent advances in embedded technology have enabled more pervasive machine learning.
Continuous Convolutional Neural Networks for Image Classification
This paper introduces the concept of continuous convolution to neural networks and deep learning applications in general.
Bayesian optimisation under uncertain inputs
In this context, we propose an upper confidence bound (UCB) algorithm for BO problems where both the outcome of a query and the true query location are uncertain.
Bayesian Learning of Conditional Kernel Mean Embeddings for Automatic Likelihood-Free Inference
In likelihood-free settings where likelihood evaluations are intractable, approximate Bayesian computation (ABC) addresses the formidable inference task to discover plausible parameters of simulation programs that explain the observations.
Bayesian Deconditional Kernel Mean Embeddings
Conditional kernel mean embeddings form an attractive nonparametric framework for representing conditional means of functions, describing the observation processes for many complex models.
Kernel Trajectory Maps for Multi-Modal Probabilistic Motion Prediction
Understanding the dynamics of an environment, such as the movement of humans and vehicles, is crucial for agents to achieve long-term autonomy in urban environments.
Speeding Up Iterative Closest Point Using Stochastic Gradient Descent
Sensors producing 3D point clouds such as 3D laser scanners and RGB-D cameras are widely used in robotics, be it for autonomous driving or manipulation.
Occ-Traj120: Occupancy Maps with Associated Trajectories
Trajectory modelling had been the principal research area for understanding and anticipating human behaviour.
Bayesian Local Sampling-based Planning
In this work, we introduce a local sampling-based motion planner with a Bayesian learning scheme for modelling an adaptive sampling proposal distribution.
OCTNet: Trajectory Generation in New Environments from Past Experiences
This generally involves the prediction and understanding of motion patterns of dynamic entities, such as vehicles and people, in the surroundings.
IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data
For simple short-horizon manipulation tasks with modest variation in task instances, offline learning from a small set of demonstrations can produce controllers that successfully solve the task.
Bayesian Curiosity for Efficient Exploration in Reinforcement Learning
Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like $\epsilon$-greedy.
Dynamic Hilbert Maps: Real-Time Occupancy Predictions in Changing Environment
This paper addresses the problem of learning instantaneous occupancy levels of dynamic environments and predicting future occupancy levels.
Semi-supervised Learning Approach to Generate Neuroimaging Modalities with Adversarial Training
On the other hand, there is smaller fraction of examples that contain all modalities (\emph{paired} data) and furthermore each modality is high dimensional when compared to number of datapoints.
Reinforcement Learning with Probabilistically Complete Exploration
Balancing exploration and exploitation remains a key challenge in reinforcement learning (RL).
Intrinsic Exploration as Multi-Objective RL
To overcome this problem, we propose a framework based on multi-objective RL where both exploration and exploitation are being optimized as separate objectives.
Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning
Traditional robotic approaches rely on an accurate model of the environment, a detailed description of how to perform the task, and a robust perception system to keep track of the current state.
Heteroscedastic Bayesian Optimisation for Stochastic Model Predictive Control
Model predictive control (MPC) has been successful in applications involving the control of complex physical systems.
Sparse Spectrum Warped Input Measures for Nonstationary Kernel Learning
The resulting method is based on sparse spectrum Gaussian processes, enabling closed-form solutions, and is extensible to a stacked construction to capture more complex patterns.
Learning to Plan Optimally with Flow-based Motion Planner
The normalising flow based distribution uses simple invertible transformations that are very computationally efficient, and our optimisation formulation explicitly avoids mode collapse in contrast to other existing learning-based planners.
Anticipatory Navigation in Crowds by Probabilistic Prediction of Pedestrian Future Movements
Critical for the coexistence of humans and robots in dynamic environments is the capability for agents to understand each other's actions, and anticipate their movements.
Fast Uncertainty Quantification for Deep Object Pose Estimation
Deep learning-based object pose estimators are often unreliable and overconfident especially when the input image is outside the training domain, for instance, with sim2real transfer.
Stein Variational Model Predictive Control
By casting MPC as a Bayesian inference problem, we employ variational methods for posterior computation, naturally encoding the complexity and multi-modality of the decision making problem.
PyEquIon: A Python Package For Automatic Speciation Calculations of Aqueous Electrolyte Solutions
In several industrial applications, such as crystallization, pollution control, and flow assurance, an accurate understanding of the aqueous electrolyte solutions is crucial.
Chemical Physics
Stein ICP for Uncertainty Estimation in Point Cloud Matching
Quantification of uncertainty in point cloud matching is critical in many tasks such as pose estimation, sensor fusion, and grasping.
Learning ODEs via Diffeomorphisms for Fast and Robust Integration
Advances in differentiable numerical integrators have enabled the use of gradient descent techniques to learn ordinary differential equations (ODEs).
Probabilistic Trajectory Prediction with Structural Constraints
This distribution is then used as a prior to a constrained optimisation problem which enforces chance constraints on the trajectory distribution.
Parallelised Diffeomorphic Sampling-based Motion Planning
We propose Parallelised Diffeomorphic Sampling-based Motion Planning (PDMP).
Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulation
We address the latter problem of estimating parameters through a Bayesian inference approach that approximates a posterior distribution over simulation parameters given real sensor measurements.
Generalizing Successor Features to continuous domains for Multi-task Learning
In this paper, we consider the problem of continuous control for various robot manipulation tasks with an explicit representation that promotes skill reuse while learning multiple tasks, related through the reward function.
Learning Efficient and Robust Ordinary Differential Equations via Diffeomorphisms
Consequently, by restricting the base ODE to be amenable to integration, we can speed up and improve the robustness of integrating trajectories from the learned system.
Robot Learning from Randomized Simulations: A Review
The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data.
Optimal Transport for Distribution Adaptation in Bayesian Hilbert Maps
Parameters are one of the most critical components of machine learning models.
Distributional Bayesian optimisation for variational inference on black-box simulators
Inverse problems are ubiquitous in natural sciences and refer to the challenging task of inferring complex and potentially multi-modal posterior distributions over hidden parameters given a set of observations.
A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulation
Deformable object manipulation remains a challenging task in robotics research.
Bayesian Optimisation for Robust Model Predictive Control under Model Parameter Uncertainty
We propose an adaptive optimisation approach for tuning stochastic model predictive control (MPC) hyper-parameters while jointly estimating probability distributions of the transition model parameters based on performance rewards.
L4KDE: Learning for KinoDynamic Tree Expansion
We study the kinodynamic variants of tree-based planning, where we have known system dynamics and kinematic constraints.
Adaptive Model Predictive Control by Learning Classifiers
Stochastic model predictive control has been a successful and robust control framework for many robotics tasks where the system dynamics model is slightly inaccurate or in the presence of environment disturbances.
DiSECt: A Differentiable Simulator for Parameter Inference and Control in Robotic Cutting
In this work, we present DiSECt: the first differentiable simulator for cutting soft materials.
Accelerated Policy Learning with Parallel Differentiable Simulation
In this work we present a high-performance differentiable simulator and a new policy learning algorithm (SHAC) that can effectively leverage simulation gradients, even in the presence of non-smoothness.
Renaissance Robot: Optimal Transport Policy Fusion for Learning Diverse Skills
Deep reinforcement learning (RL) is a promising approach to solving complex robotics problems.
Learning to Simulate Tree-Branch Dynamics for Manipulation
We propose to use a simulation driven inverse inference approach to model the dynamics of tree branches under manipulation.
Path Signatures for Diversity in Probabilistic Trajectory Optimisation
Motion planning can be cast as a trajectory optimisation problem where a cost is minimised as a function of the trajectory being generated.
STAMP: Differentiable Task and Motion Planning via Stein Variational Gradient Descent
In this paper, we propose a novel approach to TAMP that relaxes discrete-and-continuous TAMP problems into inference problems on a continuous domain.
Signatures Meet Dynamic Programming: Generalizing Bellman Equations for Trajectory Following
As a specific case of our framework, we devise a model predictive control method for path tracking.
