Author name cluster

Florian Golemo

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

2 author rows

JMLR Journal 2023 Journal Article

Towards Learning to Imitate from a Single Video Demonstration

Glen Berseth
Florian Golemo
Christopher Pal

Agents that can learn to imitate behaviours observed in video -- without having direct access to internal state or action information of the observed agent -- are more suitable for learning in the natural world. However, formulating a reinforcement learning (RL) agent that facilitates this goal remains a significant challenge. We approach this challenge using contrastive training to learn a reward function by comparing an agent's behaviour with a single demonstration. We use a Siamese recurrent neural network architecture to learn rewards in space and time between motion clips while training an RL policy to minimize this distance. Through experimentation, we also find that the inclusion of multi-task data and additional image encoding losses improve the temporal consistency of the learned rewards and, as a result, significantly improve policy learning. We demonstrate our approach on simulated humanoid, dog, and raptor agents in 2D and quadruped and humanoid agents in 3D. We show that our method outperforms current state-of-the-art techniques and can learn to imitate behaviours from a single video demonstration. [abs] [ pdf ][ bib ] &copy JMLR 2023. ( edit, beta )

PDF Details

ICLR Conference 2022 Conference Paper

Latent Variable Sequential Set Transformers for Joint Multi-Agent Motion Prediction

Roger Girgis
Florian Golemo
Felipe Codevilla
Martin Weiss
Jim Aldon D'Souza
Samira Ebrahimi Kahou
Felix Heide
Christopher Pal

Robust multi-agent trajectory prediction is essential for the safe control of robotic systems. A major challenge is to efficiently learn a representation that approximates the true joint distribution of contextual, social, and temporal information to enable planning. We propose Latent Variable Sequential Set Transformers which are encoder-decoder architectures that generate scene-consistent multi-agent trajectories. We refer to these architectures as “AutoBots”. The encoder is a stack of interleaved temporal and social multi-head self-attention (MHSA) modules which alternately perform equivariant processing across the temporal and social dimensions. The decoder employs learnable seed parameters in combination with temporal and social MHSA modules allowing it to perform inference over the entire future scene in a single forward pass efficiently. AutoBots can produce either the trajectory of one ego-agent or a distribution over the future trajectories for all agents in the scene. For the single-agent prediction case, our model achieves top results on the global nuScenes vehicle motion prediction leaderboard, and produces strong results on the Argoverse vehicle prediction challenge. In the multi-agent setting, we evaluate on the synthetic partition of TrajNet++ dataset to showcase the model’s socially-consistent predictions. We also demonstrate our model on general sequences of sets and provide illustrative experiments modelling the sequential structure of the multiple strokes that make up symbols in the Omniglot data. A distinguishing feature of AutoBots is that all models are trainable on a single desktop GPU (1080 Ti) in under 48h.

Details

ICLR Conference 2021 Conference Paper

gradSim: Differentiable simulation for system identification and visuomotor control

Krishna Murthy Jatavallabhula
Miles Macklin
Florian Golemo
Vikram Voleti
Linda Petrini
Martin Weiss
Breandan Considine
Jérôme Parent-Lévesque

In this paper, we tackle the problem of estimating object physical properties such as mass, friction, and elasticity directly from video sequences. Such a system identification problem is fundamentally ill-posed due to the loss of information during image formation. Current best solutions to the problem require precise 3D labels which are labor intensive to gather, and infeasible to create for many systems such as deformable solids or cloth. In this work we present gradSim, a framework that overcomes the dependence on 3D supervision by combining differentiable multiphysics simulation and differentiable rendering to jointly model the evolution of scene dynamics and image formation. This unique combination enables backpropagation from pixels in a video sequence through to the underlying physical attributes that generated them. Furthermore, our unified computation graph across dynamics and rendering engines enables the learning of challenging visuomotor control tasks, without relying on state-based (3D) supervision, while obtaining performance competitive to/better than techniques that require precise 3D labels.

Details

NeurIPS Conference 2020 Conference Paper

Unsupervised Learning of Dense Visual Representations

Pedro O. O. Pinheiro
Amjad Almahairi
Ryan Benmalek
Florian Golemo
Aaron C. Courville

Contrastive self-supervised learning has emerged as a promising approach to unsupervised visual representation learning. In general, these methods learn global (image-level) representations that are invariant to different views (i. e. , compositions of data augmentation) of the same image. However, many visual understanding tasks require dense (pixel-level) representations. In this paper, we propose View-Agnostic Dense Representation (VADeR) for unsupervised learning of dense representations. VADeR learns pixelwise representations by forcing local features to remain constant over different viewing conditions. Specifically, this is achieved through pixel-level contrastive learning: matching features (that is, features that describes the same location of the scene on different views) should be close in an embedding space, while non-matching features should be apart. VADeR provides a natural representation for dense prediction tasks and transfers well to downstream tasks. Our method outperforms ImageNet supervised pretraining (and strong unsupervised baselines) in multiple dense prediction tasks.

PDF Details

RLDM Conference 2019 Conference Abstract

Active Domain Randomization

Florian Golemo
Bhairav Mehta
Manfred R Diaz
Liam Paull

Domain randomization is a popular technique for zero-shot domain transfer, often used in rein- forcement learning when the target domain is unknown or cannot easily be used for training. In this work, we empirically examine the effects of domain randomization on agent generalization and sample complexity. Our experiments show that domain randomization may lead to suboptimal policies even in simple simulated tasks, which we attribute to the uniform sampling of environment parameters. We propose Active Domain Randomization, a novel algorithm that learns a sampling strategy of randomization parameters. Our method looks for the most informative environment variations within the given randomization ranges by leveraging the differences of policy rollouts in randomized and reference environment instances. We find that training more frequently on these proposed instances leads to faster and better agent generalization. In addition, when domain randomization and policy transfer fail, Active Domain Randomization offers more insight into the deficiencies of both the chosen parameter ranges and the learned policy, allowing for more focused debugging. Our experiments across various physics-based simulated tasks show that this enhancement leads to more robust policies, all while improving sample efficiency over previous methods.

PDF Details

IROS Conference 2017 Conference Paper

A multimodal dataset for object model learning from natural human-robot interaction

Pablo Azagra
Florian Golemo
Yoan Mollard
Manuel Lopes 0001
Javier Civera 0001
Ana C. Murillo

Learning object models in the wild from natural human interactions is an essential ability for robots to perform general tasks. In this paper we present a robocentric multimodal dataset addressing this key challenge. Our dataset focuses on interactions where the user teaches new objects to the robot in various ways. It contains synchronized recordings of visual (3 cameras) and audio data which provide a challenging evaluation framework for different tasks. Additionally, we present an end-to-end system that learns object models using object patches extracted from the recorded natural interactions. Our proposed pipeline follows these steps: (a) recognizing the interaction type, (b) detecting the object that the interaction is focusing on, and (c) learning the models from the extracted data. Our main contribution lies in the steps towards identifying the target object patches of the images. We demonstrate the advantages of combining language and visual features for the interaction recognition and use multiple views to improve the object modelling. Our experimental results show that our dataset is challenging due to occlusions and domain change with respect to typical object learning frameworks. The performance of common out-of-the-box classifiers trained on our data is low. We demonstrate that our algorithm outperforms such baselines.

Details