305 citations · 765 across the 23 of their papers we have counts for
28 papers
InfraParis: A multi-modal and multi-task autonomous driving dataset
Gianni Franchi, Marwane Hariat, Xuanlong Yu +3
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. Cons…
Are standard Object Segmentation models sufficient for Learning Affordance Segmentation?
Hugo Caselles-Dupré, Michael Garcia-Ortiz, David Filliat
Affordances are the possibilities of actions the environment offers to the individual. Ordinary objects (hammer, knife) usually have many affordances (grasping, pounding, cutting),…
SCOD: Active Object Detection for Embodied Agents using Sensory Commutativity of Action Sequences
Hugo Caselles-Dupré, Michael Garcia-Ortiz, David Filliat
We introduce SCOD (Sensory Commutativity Object Detection), an active method for movable and immovable object detection. SCOD exploits the commutative properties of action sequence…
Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey
Thomas Rojat, Raphaël Puget, David Filliat +3
Most of state of the art methods applied on time series consist of deep learning methods that are too complex to be interpreted. This lack of interpretability is a major drawback,…
DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics
Stephane Doncieux, Nicolas Bredeche, Léni Le Goff +9
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. Learning algorithm…
On the Sensory Commutativity of Action Sequences for Embodied Agents
Hugo Caselles-Dupré, Michael Garcia-Ortiz, David Filliat
Perception of artificial agents is one the grand challenges of AI research. Deep Learning and data-driven approaches are successful on constrained problems where perception can be…
Regularization Shortcomings for Continual Learning
Timothée Lesort, Andrei Stoian, David Filliat
In most machine learning algorithms, training data is assumed to be independent and identically distributed (iid). When it is not the case, the algorithm's performances are challen…
DisCoRL: Continual Reinforcement Learning via Policy Distillation
René Traoré, Hugo Caselles-Dupré, Timothée Lesort +4
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…
Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges
Timothée Lesort, Vincenzo Lomonaco, Andrei Stoian +3
Continual learning (CL) is a particular machine learning paradigm where the data distribution and learning objective changes through time, or where all the training data and object…
Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer
René Traoré, Hugo Caselles-Dupré, Timothée Lesort +3
We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encoun…
Symmetry-Based Disentangled Representation Learning requires Interaction with Environments
Hugo Caselles-Dupré, Michael Garcia-Ortiz, David Filliat
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 construc…
S-TRIGGER: Continual State Representation Learning via Self-Triggered Generative Replay
Hugo Caselles-Dupré, Michael Garcia-Ortiz, David Filliat
We consider the problem of building a state representation model for control, in a continual learning setting. As the environment changes, the aim is to efficiently compress the se…
Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics
Antonin Raffin, Ashley Hill, René Traoré +3
Scaling end-to-end reinforcement learning to control real robots from vision presents a series of challenges, in particular in terms of sample efficiency. Against end-to-end learni…
Generative Models from the perspective of Continual Learning
Timothée Lesort, Hugo Caselles-Dupré, Michael Garcia-Ortiz +2
Which generative model is the most suitable for Continual Learning? This paper aims at evaluating and comparing generative models on disjoint sequential image generation tasks. We…
Don't forget, there is more than forgetting: new metrics for Continual Learning
Natalia Díaz-Rodríguez, Vincenzo Lomonaco, David Filliat +1
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…
Learning structure-from-motion from motion
Clément Pinard, Laure Chevalley, Antoine Manzanera +1
This work is based on a questioning of the quality metrics used by deep neural networks performing depth prediction from a single image, and then of the usability of recently publi…
S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning
Antonin Raffin, Ashley Hill, René Traoré +3
State representation learning aims at learning compact representations from raw observations in robotics and control applications. Approaches used for this objective are auto-encod…
Marginal Replay vs Conditional Replay for Continual Learning
Timothée Lesort, Alexander Gepperth, Andrei Stoian +1
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 distribut…
Continual State Representation Learning for Reinforcement Learning using Generative Replay
Hugo Caselles-Dupré, Michael Garcia-Ortiz, David Filliat
We consider the problem of building a state representation model in a continual fashion. As the environment changes, the aim is to efficiently compress the sensory state's informat…
Multi range Real-time depth inference from a monocular stabilized footage using a Fully Convolutional Neural Network
Clément Pinard, Laure Chevalley, Antoine Manzanera +1
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 f…
End-to-end depth from motion with stabilized monocular videos
Clément Pinard, Laure Chevalley, Antoine Manzanera +1
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 sc…
Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning
Hugo Caselles-Dupré, Louis Annabi, Oksana Hagen +2
Flatland is a simple, lightweight environment for fast prototyping and testing of reinforcement learning agents. It is of lower complexity compared to similar 3D platforms (e.g. De…
Training Discriminative Models to Evaluate Generative Ones
Timothée Lesort, Andrei Stoain, Jean-François Goudou +1
Generative models are known to be difficult to assess. Recent works, especially on generative adversarial networks (GANs), produce good visual samples of varied categories of image…
Exploring to learn visual saliency: The RL-IAC approach
Celine Craye, Timothee Lesort, David Filliat +1
The problem of object localization and recognition on autonomous mobile robots is still an active topic. In this context, we tackle the problem of learning a model of visual salien…