Search Results for author:
Found 38 papers, 12 papers with code
Hierarchical Light Transformer Ensembles for Multimodal Trajectory Forecasting
Accurate trajectory forecasting is crucial for the performance of various systems, such as advanced driver-assistance systems and self-driving vehicles.
On Double Descent in Reinforcement Learning with LSTD and Random Features
We identify the ratio between the number of parameters and the number of visited states as a crucial factor and define over-parameterization as the regime when it is larger than one.
InfraParis: A multi-modal and multi-task autonomous driving dataset
Current deep neural networks (DNNs) for autonomous driving computer vision are typically trained on specific datasets that only involve a single type of data and urban scenes.
VIBR: Learning View-Invariant Value Functions for Robust Visual Control
In this work, we tackle the problem of robust visual control at its core and present VIBR (View-Invariant Bellman Residuals), a method that combines multi-view training and invariant prediction to reduce out-of-distribution (OOD) generalization gap for RL based visuomotor control.
Latent Discriminant deterministic Uncertainty
Predictive uncertainty estimation is essential for deploying Deep Neural Networks in real-world autonomous systems.
MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks
However, disentangling the different types and sources of uncertainty is non trivial for most datasets, especially since there is no ground truth for uncertainty.
A study of deep perceptual metrics for image quality assessment
Several metrics exist to quantify the similarity between images, but they are inefficient when it comes to measure the similarity of highly distorted images.
Fourier Features in Reinforcement Learning with Neural Networks
To the best of our knowledge, this is the first reported application of Fourier features in Deep RL.
POAR: Efficient Policy Optimization via Online Abstract State Representation Learning
Firstly, We engage RL loss to assist in updating SRL model so that the states can evolve to meet the demand of RL and maintain a good physical interpretation.
SCOD: Active Object Detection for Embodied Agents using Sensory Commutativity of Action Sequences
We introduce SCOD (Sensory Commutativity Object Detection), an active method for movable and immovable object detection.
Are standard Object Segmentation models sufficient for Learning Affordance Segmentation?
We conclude that the problem of supervised affordance segmentation is included in the problem of object segmentation and argue that better benchmarks for affordance learning should include action capacities.
Evaluating Robustness over High Level Driving Instruction for Autonomous Driving
In recent years, we have witnessed increasingly high performance in the field of autonomous end-to-end driving.
EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case
We tackle such problem by considering the symbolic knowledge is expressed in form of a domain expert knowledge graph.
Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey
Most of state of the art methods applied on time series consist of deep learning methods that are too complex to be interpreted.
DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics
Robots are still limited to controlled conditions, that the robot designer knows with enough details to endow the robot with the appropriate models or behaviors.
On the Sensory Commutativity of Action Sequences for Embodied Agents
In such case, for autonomous embodied agents with first-person sensors, perception can be learned end-to-end to solve particular tasks.
Regularization Shortcomings for Continual Learning
In most machine learning algorithms, training data is assumed to be independent and identically distributed (iid).
DisCoRL: Continual Reinforcement Learning via Policy Distillation
In multi-task reinforcement learning there are two main challenges: at training time, the ability to learn different policies with a single model; at test time, inferring which of those policies applying without an external signal.
Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges
An important challenge for machine learning is not necessarily finding solutions that work in the real world but rather finding stable algorithms that can learn in real world.
Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer
We focus on the problem of teaching a robot to solve tasks presented sequentially, i. e., in a continual learning scenario.
Symmetry-Based Disentangled Representation Learning requires Interaction with Environments
Finding a generally accepted formal definition of a disentangled representation in the context of an agent behaving in an environment is an important challenge towards the construction of data-efficient autonomous agents.
S-TRIGGER: Continual State Representation Learning via Self-Triggered Generative Replay
As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge, and then use Reinforcement Learning on the resulting features for efficient policy learning.
Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics
Scaling end-to-end reinforcement learning to control real robots from vision presents a series of challenges, in particular in terms of sample efficiency.
Generative Models from the perspective of Continual Learning
We experiment with sequential tasks on three commonly used benchmarks for Continual Learning (MNIST, Fashion MNIST and CIFAR10).
Don't forget, there is more than forgetting: new metrics for Continual Learning
Continual learning consists of algorithms that learn from a stream of data/tasks continuously and adaptively thought time, enabling the incremental development of ever more complex knowledge and skills.
Marginal Replay vs Conditional Replay for Continual Learning
We present a new replay-based method of continual classification learning that we term "conditional replay" which generates samples and labels together by sampling from a distribution conditioned on the class.
Continual State Representation Learning for Reinforcement Learning using Generative Replay
As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge.
S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning
State representation learning aims at learning compact representations from raw observations in robotics and control applications.
End-to-end depth from motion with stabilized monocular videos
We propose a depth map inference system from monocular videos based on a novel dataset for navigation that mimics aerial footage from gimbal stabilized monocular camera in rigid scenes.
Multi range Real-time depth inference from a monocular stabilized footage using a Fully Convolutional Neural Network
Using a neural network architecture for depth map inference from monocular stabilized videos with application to UAV videos in rigid scenes, we propose a multi-range architecture for unconstrained UAV flight, leveraging flight data from sensors to make accurate depth maps for uncluttered outdoor environment.
Learning structure-from-motion from motion
We then present results on a synthetic dataset that we believe to be more representative of typical UAV scenes.
Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning
Flatland is a simple, lightweight environment for fast prototyping and testing of reinforcement learning agents.
Training Discriminative Models to Evaluate Generative Ones
By comparing results with different generated datasets we are able to classify and compare generative models.
Exploring to learn visual saliency: The RL-IAC approach
On the other hand, we investigate an autonomous exploration technique to efficiently learn such a saliency model.
State Representation Learning for Control: An Overview
State representation learning (SRL) focuses on a particular kind of representation learning where learned features are in low dimension, evolve through time, and are influenced by actions of an agent.
Evaluation of generative networks through their data augmentation capacity
This mixture of real and generated data is thus used to train a classifier which is afterwards tested on a given labeled test dataset.
Unsupervised state representation learning with robotic priors: a robustness benchmark
We reproduce this simplification process using a neural network to build a low dimensional state representation of the world from images acquired by a robot.
Gated networks: an inventory
Gated networks are networks that contain gating connections, in which the outputs of at least two neurons are multiplied.
