Search Results for author: Florian Shkurti

Found 30 papers, 12 papers with code

ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization

no code implementations13 Jan 2024 Kourosh Darvish, Marta Skreta, Yuchi Zhao, Naruki Yoshikawa, Sagnik Som, Miroslav Bogdanovic, Yang Cao, Han Hao, Haoping Xu, Alán Aspuru-Guzik, Animesh Garg, Florian Shkurti

Despite the many benefits incurred by the integration of advanced and special-purpose lab equipment, many aspects of experimentation are still manually conducted by chemists, for example, polishing an electrode in electrochemistry experiments.


ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning

no code implementations28 Sep 2023 Qiao Gu, Alihusein Kuwajerwala, Sacha Morin, Krishna Murthy Jatavallabhula, Bipasha Sen, Aditya Agarwal, Corban Rivera, William Paul, Kirsty Ellis, Rama Chellappa, Chuang Gan, Celso Miguel de Melo, Joshua B. Tenenbaum, Antonio Torralba, Florian Shkurti, Liam Paull

We demonstrate the utility of this representation through a number of downstream planning tasks that are specified through abstract (language) prompts and require complex reasoning over spatial and semantic concepts.

Exploring Continual Learning of Diffusion Models

no code implementations27 Mar 2023 Michał Zając, Kamil Deja, Anna Kuzina, Jakub M. Tomczak, Tomasz Trzciński, Florian Shkurti, Piotr Miłoś

Diffusion models have achieved remarkable success in generating high-quality images thanks to their novel training procedures applied to unprecedented amounts of data.

Benchmarking Continual Learning +1

Preserving Linear Separability in Continual Learning by Backward Feature Projection

1 code implementation CVPR 2023 Qiao Gu, Dongsub Shim, Florian Shkurti

To achieve a better stability-plasticity trade-off, we propose Backward Feature Projection (BFP), a method for continual learning that allows the new features to change up to a learnable linear transformation of the old features.

Continual Learning Knowledge Distillation

Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers

1 code implementation CVPR 2023 Cong Wei, Brendan Duke, Ruowei Jiang, Parham Aarabi, Graham W. Taylor, Florian Shkurti

Equipped with the learned unstructured attention pattern, sparse attention ViT (Sparsifiner) produces a superior Pareto-optimal trade-off between FLOPs and top-1 accuracy on ImageNet compared to token sparsity.

MVTrans: Multi-View Perception of Transparent Objects

no code implementations22 Feb 2023 Yi Ru Wang, Yuchi Zhao, Haoping Xu, Saggi Eppel, Alan Aspuru-Guzik, Florian Shkurti, Animesh Garg

Transparent object perception is a crucial skill for applications such as robot manipulation in household and laboratory settings.

Depth Estimation Object +5

ConceptFusion: Open-set Multimodal 3D Mapping

1 code implementation14 Feb 2023 Krishna Murthy Jatavallabhula, Alihusein Kuwajerwala, Qiao Gu, Mohd Omama, Tao Chen, Alaa Maalouf, Shuang Li, Ganesh Iyer, Soroush Saryazdi, Nikhil Keetha, Ayush Tewari, Joshua B. Tenenbaum, Celso Miguel de Melo, Madhava Krishna, Liam Paull, Florian Shkurti, Antonio Torralba

ConceptFusion leverages the open-set capabilities of today's foundation models pre-trained on internet-scale data to reason about concepts across modalities such as natural language, images, and audio.

Autonomous Driving Robot Navigation

NeurIPS 2022 Competition: Driving SMARTS

no code implementations14 Nov 2022 Amir Rasouli, Randy Goebel, Matthew E. Taylor, Iuliia Kotseruba, Soheil Alizadeh, Tianpei Yang, Montgomery Alban, Florian Shkurti, Yuzheng Zhuang, Adam Scibior, Kasra Rezaee, Animesh Garg, David Meger, Jun Luo, Liam Paull, Weinan Zhang, Xinyu Wang, Xi Chen

The proposed competition supports methodologically diverse solutions, such as reinforcement learning (RL) and offline learning methods, trained on a combination of naturalistic AD data and open-source simulation platform SMARTS.

Autonomous Driving Reinforcement Learning (RL)

Policy-Guided Lazy Search with Feedback for Task and Motion Planning

no code implementations25 Oct 2022 Mohamed Khodeir, Atharv Sonwane, Ruthrash Hari, Florian Shkurti

PDDLStream solvers have recently emerged as viable solutions for Task and Motion Planning (TAMP) problems, extending PDDL to problems with continuous action spaces.

Motion Planning Task and Motion Planning

SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos

1 code implementation CVPR 2022 Salar Hosseini Khorasgani, Yuxuan Chen, Florian Shkurti

One of the key reasons for this is that sampling pairs of similar video clips, a required step for many self-supervised contrastive learning methods, is currently done conservatively to avoid false positives.

 Ranked #1 on Self-Supervised Action Recognition on UCF101 (Pre-Training Dataset metric)

Action Classification Clustering +6

Learning to Search in Task and Motion Planning with Streams

no code implementations25 Nov 2021 Mohamed Khodeir, Ben Agro, Florian Shkurti

Task and motion planning problems in robotics combine symbolic planning over discrete task variables with motion optimization over continuous state and action variables.

Graph Neural Network Motion Planning +1

Augmenting Imitation Experience via Equivariant Representations

no code implementations14 Oct 2021 Dhruv Sharma, Alihusein Kuwajerwala, Florian Shkurti

The robustness of visual navigation policies trained through imitation often hinges on the augmentation of the training image-action pairs.

Data Augmentation Visual Navigation

Seeing Glass: Joint Point Cloud and Depth Completion for Transparent Objects

no code implementations30 Sep 2021 Haoping Xu, Yi Ru Wang, Sagi Eppel, Alàn Aspuru-Guzik, Florian Shkurti, Animesh Garg

To address the shortcomings of existing transparent object data collection schemes in literature, we also propose an automated dataset creation workflow that consists of robot-controlled image collection and vision-based automatic annotation.

Depth Completion Transparent objects

Effects of Conservatism on Offline Learning

no code implementations29 Sep 2021 Karush Suri, Florian Shkurti

The proposed answer studies conservatism in light of value function optimization, approximate objectives that upper bound underestimations and behavior cloning as auxilary regularization objective.

Continuous Control Reinforcement Learning (RL)

Physics-based Human Motion Estimation and Synthesis from Videos

no code implementations ICCV 2021 Kevin Xie, Tingwu Wang, Umar Iqbal, Yunrong Guo, Sanja Fidler, Florian Shkurti

By enabling learning of motion synthesis from video, our method paves the way for large-scale, realistic and diverse motion synthesis.

Motion Estimation Motion Synthesis +1

LOHO: Latent Optimization of Hairstyles via Orthogonalization

1 code implementation CVPR 2021 Rohit Saha, Brendan Duke, Florian Shkurti, Graham W. Taylor, Parham Aarabi

Therefore, we propose Latent Optimization of Hairstyles via Orthogonalization (LOHO), an optimization-based approach using GAN inversion to infill missing hair structure details in latent space during hairstyle transfer.


Latent Skill Planning for Exploration and Transfer

no code implementations ICLR 2021 Kevin Xie, Homanga Bharadhwaj, Danijar Hafner, Animesh Garg, Florian Shkurti

To quickly solve new tasks in complex environments, intelligent agents need to build up reusable knowledge.

Shaping Rewards for Reinforcement Learning with Imperfect Demonstrations using Generative Models

no code implementations2 Nov 2020 Yuchen Wu, Melissa Mozifian, Florian Shkurti

Unlike the majority of existing methods that assume optimal demonstrations and incorporate the demonstration data as hard constraints on policy optimization, we instead incorporate demonstration data as advice in the form of a reward shaping potential trained as a generative model of states and actions.

Imitation Learning reinforcement-learning +1

Conservative Safety Critics for Exploration

no code implementations ICLR 2021 Homanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart, Sergey Levine, Florian Shkurti, Animesh Garg

Safe exploration presents a major challenge in reinforcement learning (RL): when active data collection requires deploying partially trained policies, we must ensure that these policies avoid catastrophically unsafe regions, while still enabling trial and error learning.

Reinforcement Learning (RL) Safe Exploration

Continual Model-Based Reinforcement Learning with Hypernetworks

1 code implementation25 Sep 2020 Yizhou Huang, Kevin Xie, Homanga Bharadhwaj, Florian Shkurti

Effective planning in model-based reinforcement learning (MBRL) and model-predictive control (MPC) relies on the accuracy of the learned dynamics model.

Continual Learning Model-based Reinforcement Learning +3

LEAF: Latent Exploration Along the Frontier

no code implementations21 May 2020 Homanga Bharadhwaj, Animesh Garg, Florian Shkurti

We target the challenging problem of policy learning from initial and goal states specified as images, and do not assume any access to the underlying ground-truth states of the robot and the environment.

Model-Predictive Control via Cross-Entropy and Gradient-Based Optimization

1 code implementation L4DC 2020 Homanga Bharadhwaj, Kevin Xie, Florian Shkurti

Recent works in high-dimensional model-predictive control and model-based reinforcement learning with learned dynamics and reward models have resorted to population-based optimization methods, such as the Cross-Entropy Method (CEM), for planning a sequence of actions.

Model-based Reinforcement Learning Model Predictive Control

One-Shot Informed Robotic Visual Search in the Wild

1 code implementation22 Mar 2020 Karim Koreitem, Florian Shkurti, Travis Manderson, Wei-Di Chang, Juan Camilo Gamboa Higuera, Gregory Dudek

In this paper we propose a method that enables informed visual navigation via a learned visual similarity operator that guides the robot's visual search towards parts of the scene that look like an exemplar image, which is given by the user as a high-level specification for data collection.

Navigate Representation Learning +2

Diversity inducing Information Bottleneck in Model Ensembles

1 code implementation10 Mar 2020 Samarth Sinha, Homanga Bharadhwaj, Anirudh Goyal, Hugo Larochelle, Animesh Garg, Florian Shkurti

Although deep learning models have achieved state-of-the-art performance on a number of vision tasks, generalization over high dimensional multi-modal data, and reliable predictive uncertainty estimation are still active areas of research.

Out-of-Distribution Detection

Underwater Multi-Robot Convoying using Visual Tracking by Detection

1 code implementation25 Sep 2017 Florian Shkurti, Wei-Di Chang, Peter Henderson, Md Jahidul Islam, Juan Camilo Gamboa Higuera, Jimmy Li, Travis Manderson, Anqi Xu, Gregory Dudek, Junaed Sattar

We present a robust multi-robot convoying approach that relies on visual detection of the leading agent, thus enabling target following in unstructured 3-D environments.

object-detection Object Detection +1

Benchmark Environments for Multitask Learning in Continuous Domains

1 code implementation14 Aug 2017 Peter Henderson, Wei-Di Chang, Florian Shkurti, Johanna Hansen, David Meger, Gregory Dudek

As demand drives systems to generalize to various domains and problems, the study of multitask, transfer and lifelong learning has become an increasingly important pursuit.

OpenAI Gym

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