Search Results for author: Fabio Ramos

Found 64 papers, 16 papers with code

Accelerated Policy Learning with Parallel Differentiable Simulation

no code implementations ICLR 2022 Jie Xu, Viktor Makoviychuk, Yashraj Narang, Fabio Ramos, Wojciech Matusik, Animesh Garg, Miles Macklin

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.

Adaptive Model Predictive Control by Learning Classifiers

no code implementations13 Mar 2022 Rel Guzman, Rafael Oliveira, Fabio Ramos

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.

Bayesian Optimisation Density Ratio Estimation

L4KDE: Learning for KinoDynamic Tree Expansion

no code implementations2 Mar 2022 Tin Lai, Weiming Zhi, Tucker Hermans, Fabio Ramos

We study the kinodynamic variants of tree-based planning, where we have known system dynamics and kinematic constraints.

Motion Planning

Bayesian Optimisation for Robust Model Predictive Control under Model Parameter Uncertainty

no code implementations1 Mar 2022 Rel Guzman, Rafael Oliveira, Fabio Ramos

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.

Bayesian Optimisation

Robot Learning from Randomized Simulations: A Review

no code implementations1 Nov 2021 Fabio Muratore, Fabio Ramos, Greg Turk, Wenhao Yu, Michael Gienger, Jan Peters

The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data.

Generalizing Successor Features to continuous domains for Multi-task Learning

no code implementations29 Sep 2021 Melissa Mozifian, Dieter Fox, David Meger, Fabio Ramos, Animesh Garg

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.

Continuous Control Decision Making +1

Learning Efficient and Robust Ordinary Differential Equations via Diffeomorphisms

no code implementations29 Sep 2021 Weiming Zhi, Tin Lai, Lionel Ott, Edwin V Bonilla, Fabio Ramos

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.

Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulation

no code implementations18 Sep 2021 Eric Heiden, Christopher E. Denniston, David Millard, Fabio Ramos, Gaurav S. Sukhatme

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.

Bayesian Inference Code Generation

BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGym

1 code implementation9 Jul 2021 Rika Antonova, Fabio Ramos, Rafael Possas, Dieter Fox

This paper outlines BayesSimIG: a library that provides an implementation of BayesSim integrated with the recently released NVIDIA IsaacGym.


Probabilistic Trajectory Prediction with Structural Constraints

no code implementations9 Jul 2021 Weiming Zhi, Lionel Ott, Fabio Ramos

This distribution is then used as a prior to a constrained optimisation problem which enforces chance constraints on the trajectory distribution.

Trajectory Prediction

Learning ODEs via Diffeomorphisms for Fast and Robust Integration

no code implementations4 Jul 2021 Weiming Zhi, Tin Lai, Lionel Ott, Edwin V. Bonilla, Fabio Ramos

Advances in differentiable numerical integrators have enabled the use of gradient descent techniques to learn ordinary differential equations (ODEs).

Stein ICP for Uncertainty Estimation in Point Cloud Matching

2 code implementations7 Jun 2021 Fahira Afzal Maken, Fabio Ramos, Lionel Ott

Quantification of uncertainty in point cloud matching is critical in many tasks such as pose estimation, sensor fusion, and grasping.

Autonomous Driving Decision Making +2

BORE: Bayesian Optimization by Density-Ratio Estimation

1 code implementation17 Feb 2021 Louis C. Tiao, Aaron Klein, Matthias Seeger, Edwin V. Bonilla, Cedric Archambeau, Fabio Ramos

Bayesian optimization (BO) is among the most effective and widely-used blackbox optimization methods.

Density Ratio Estimation

PyEquIon: A Python Package For Automatic Speciation Calculations of Aqueous Electrolyte Solutions

no code implementations18 Jan 2021 Caio Felippe Curitiba Marcellos, Gerson Francisco da Silva Junior, Elvis do Amaral Soares, Fabio Ramos, Amaro G. Barreto Jr

In several industrial applications, such as crystallization, pollution control, and flow assurance, an accurate understanding of the aqueous electrolyte solutions is crucial.

Chemical Physics

Fast Uncertainty Quantification for Deep Object Pose Estimation

no code implementations16 Nov 2020 Guanya Shi, Yifeng Zhu, Jonathan Tremblay, Stan Birchfield, Fabio Ramos, Animashree Anandkumar, Yuke Zhu

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.

Pose Estimation

Stein Variational Model Predictive Control

no code implementations15 Nov 2020 Alexander Lambert, Adam Fishman, Dieter Fox, Byron Boots, Fabio Ramos

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.

Bayesian Inference Decision Making +1

Anticipatory Navigation in Crowds by Probabilistic Prediction of Pedestrian Future Movements

no code implementations12 Nov 2020 Weiming Zhi, Tin Lai, Lionel Ott, Fabio Ramos

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.

Learning to Plan Optimally with Flow-based Motion Planner

no code implementations21 Oct 2020 Tin Lai, Fabio Ramos

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.

Motion Planning

Multi-Objective Bayesian Optimisation and Joint Inversion for Active Sensor Fusion

1 code implementation12 Oct 2020 Sebastian Haan, Fabio Ramos, Dietmar Müller

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.

Bayesian Optimisation

Sparse Spectrum Warped Input Measures for Nonstationary Kernel Learning

no code implementations NeurIPS 2020 Anthony Tompkins, Rafael Oliveira, Fabio Ramos

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.

Gaussian Processes

Heteroscedastic Bayesian Optimisation for Stochastic Model Predictive Control

no code implementations1 Oct 2020 Rel Guzman, Rafael Oliveira, Fabio Ramos

Model predictive control (MPC) has been successful in applications involving the control of complex physical systems.

Bayesian Optimisation Continuous Control

Online Domain Adaptation for Occupancy Mapping

1 code implementation1 Jul 2020 Anthony Tompkins, Ransalu Senanayake, Fabio Ramos

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.

Autonomous Driving Domain Adaptation

Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems

2 code implementations L4DC 2020 Muhammad Asif Rana, Anqi Li, Dieter Fox, Byron Boots, Fabio Ramos, Nathan Ratliff

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.

Density Estimation

Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning

no code implementations21 May 2020 Michelle A. Lee, Carlos Florensa, Jonathan Tremblay, Nathan Ratliff, Animesh Garg, Fabio Ramos, Dieter Fox

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.

Intrinsic Exploration as Multi-Objective RL

no code implementations6 Apr 2020 Philippe Morere, Fabio Ramos

To overcome this problem, we propose a framework based on multi-objective RL where both exploration and exploitation are being optimized as separate objectives.

Continuous Control

DISCO: Double Likelihood-free Inference Stochastic Control

1 code implementation18 Feb 2020 Lucas Barcelos, Rafael Oliveira, Rafael Possas, Lionel Ott, Fabio Ramos

Accurate simulation of complex physical systems enables the development, testing, and certification of control strategies before they are deployed into the real systems.

Reinforcement Learning with Probabilistically Complete Exploration

no code implementations20 Jan 2020 Philippe Morere, Gilad Francis, Tom Blau, Fabio Ramos

Balancing exploration and exploitation remains a key challenge in reinforcement learning (RL).


Semi-supervised Learning Approach to Generate Neuroimaging Modalities with Adversarial Training

no code implementations9 Dec 2019 Harrison Nguyen, Simon Luo, Fabio Ramos

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.

Dynamic Hilbert Maps: Real-Time Occupancy Predictions in Changing Environment

no code implementations4 Dec 2019 Vitor Guizilini, Ransalu Senanayake, Fabio Ramos

This paper addresses the problem of learning instantaneous occupancy levels of dynamic environments and predicting future occupancy levels.

Bayesian Curiosity for Efficient Exploration in Reinforcement Learning

1 code implementation20 Nov 2019 Tom Blau, Lionel Ott, Fabio Ramos

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.

Efficient Exploration reinforcement-learning

IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data

no code implementations13 Nov 2019 Ajay Mandlekar, Fabio Ramos, Byron Boots, Silvio Savarese, Li Fei-Fei, Animesh Garg, Dieter Fox

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.

Distributional Bayesian optimisation for variational inference on black-box simulators

1 code implementation pproximateinference AABI Symposium 2019 Rafael Oliveira, Lionel Ott, Fabio Ramos

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.

Bayesian Optimisation reinforcement-learning +1

OCTNet: Trajectory Generation in New Environments from Past Experiences

no code implementations25 Sep 2019 Weiming Zhi, Tin Lai, Lionel Ott, Gilad Francis, Fabio Ramos

This generally involves the prediction and understanding of motion patterns of dynamic entities, such as vehicles and people, in the surroundings.

motion prediction

Bayesian Local Sampling-based Planning

no code implementations8 Sep 2019 Tin Lai, Philippe Morere, Fabio Ramos, Gilad Francis

In this work, we introduce a local sampling-based motion planner with a Bayesian learning scheme for modelling an adaptive sampling proposal distribution.

Motion Planning

Occ-Traj120: Occupancy Maps with Associated Trajectories

no code implementations5 Sep 2019 Tin Lai, Weiming Zhi, Fabio Ramos

Trajectory modelling had been the principal research area for understanding and anticipating human behaviour.

Autonomous Driving

Speeding Up Iterative Closest Point Using Stochastic Gradient Descent

1 code implementation22 Jul 2019 Fahira Afzal Maken, Fabio Ramos, Lionel Ott

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.

Autonomous Driving Pose Estimation

Kernel Trajectory Maps for Multi-Modal Probabilistic Motion Prediction

no code implementations11 Jul 2019 Weiming Zhi, Lionel Ott, Fabio Ramos

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.

motion prediction

Learning to Plan Hierarchically from Curriculum

1 code implementation18 Jun 2019 Philippe Morere, Lionel Ott, Fabio Ramos

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.

BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators

1 code implementation4 Jun 2019 Fabio Ramos, Rafael Carvalhaes Possas, Dieter Fox

We introduce BayesSim, a framework for robotics simulations allowing a full Bayesian treatment for the parameters of the simulator.

Motion Planning

Bayesian Deconditional Kernel Mean Embeddings

no code implementations1 Jun 2019 Kelvin Hsu, Fabio Ramos

Conditional kernel mean embeddings form an attractive nonparametric framework for representing conditional means of functions, describing the observation processes for many complex models.

Gaussian Processes

Bayesian Learning of Conditional Kernel Mean Embeddings for Automatic Likelihood-Free Inference

no code implementations3 Mar 2019 Kelvin Hsu, Fabio Ramos

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 optimisation under uncertain inputs

no code implementations21 Feb 2019 Rafael Oliveira, Lionel Ott, Fabio Ramos

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 Optimisation

Hyperparameter Learning for Conditional Kernel Mean Embeddings with Rademacher Complexity Bounds

1 code implementation1 Sep 2018 Kelvin Hsu, Richard Nock, Fabio Ramos

Conditional kernel mean embeddings are nonparametric models that encode conditional expectations in a reproducing kernel Hilbert space.

Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference

no code implementations5 Jun 2018 Louis C. Tiao, Edwin V. Bonilla, Fabio Ramos

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.

Bayesian Inference Variational Inference

Index Set Fourier Series Features for Approximating Multi-dimensional Periodic Kernels

no code implementations14 May 2018 Anthony Tompkins, Fabio Ramos

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.

Gaussian Processes

Learning Non-Stationary Space-Time Models for Environmental Monitoring

no code implementations27 Apr 2018 Sahil Garg, Amarjeet Singh, Fabio Ramos

One of the primary aspects of sustainable development involves accurate understanding and modeling of environmental phenomena.

Adaptive Sensing for Learning Nonstationary Environment Models

no code implementations26 Apr 2018 Sahil Garg, Amarjeet Singh, Fabio Ramos

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.

Gaussian Processes

Correcting differences in multi-site neuroimaging data using Generative Adversarial Networks

no code implementations26 Mar 2018 Harrison Nguyen, Richard W. Morris, Anthony W. Harris, Mayuresh S. Korgoankar, Fabio Ramos

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

no code implementations17 Feb 2018 Rafael Oliveira, Fernando H. M. Rocha, Lionel Ott, Vitor Guizilini, Fabio Ramos, Valdir Grassi Jr

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 Car Racing

Continuous Convolutional Neural Networks for Image Classification

no code implementations ICLR 2018 Vitor Guizilini, Fabio Ramos

This paper introduces the concept of continuous convolution to neural networks and deep learning applications in general.

Classification General Classification +1

Bayesian Optimisation for Safe Navigation under Localisation Uncertainty

no code implementations7 Sep 2017 Rafael Oliveira, Lionel Ott, Vitor Guizilini, Fabio Ramos

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.

Bayesian Optimisation

Urban Scene Segmentation with Laser-Constrained CRFs

no code implementations7 Jan 2017 Charika De Alvis, Lionel Ott, Fabio Ramos

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.

Scene Segmentation

Online Adaptation of Deep Architectures with Reinforcement Learning

no code implementations8 Aug 2016 Thushan Ganegedara, Lionel Ott, Fabio Ramos

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.

Denoising online learning +1

Simple Online and Realtime Tracking

50 code implementations2 Feb 2016 Alex Bewley, ZongYuan Ge, Lionel Ott, Fabio Ramos, Ben Upcroft

This paper explores a pragmatic approach to multiple object tracking where the main focus is to associate objects efficiently for online and realtime applications.

Multiple Object Tracking

Integer Programming Relaxations for Integrated Clustering and Outlier Detection

no code implementations6 Mar 2014 Lionel Ott, Linsey Pang, Fabio Ramos, David Howe, Sanjay Chawla

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).

Outlier Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.