Publications related to Complexity and Similarity Metrics for Unsupervised Identification of Programming Methods for Robot Cooking Tasks

Related publications (17)

Scaling the Modalities in Multimodal Foundation Models

Having a single neural network to handle a wide and varied range of tasks and modalities has been a long-standing goal. Such a model brings notable advantages, such as test-time computational efficiency, modality fusion, and reduced model size. Our goal in ...

EPFL2025

Programming Light Propagation for Efficient Artificial Intelligence

Ilker Oguz

Contemporary artificial intelligence (AI) models' exponentially growing complexity translates to their expanding skill sets. They can create language or image content mimicking human creativity and understanding, becoming indispensable tools in education, ...

EPFL2025

From Preprocessing to Evaluation: The Role of External Knowledge in Advancing Language Models and Machine Translation

Georgios Vernikos

Machine translation (MT) systems and language models (LMs) have demonstrated impressive performance in recent years, driven by advances in architecture, algorithms, and the scaling of parameters and training data. Despite the ability of these models to int ...

EPFL2025

VP-STO: Via-point-based Stochastic Trajectory Optimization for Reactive Robot Behavior

Sylvain Calinon, Julius Maximilian Jankowski

Achieving reactive robot behavior in complex dynamic environments is still challenging as it relies on being able to solve trajectory optimization problems quickly enough, such that we can replan the future motion at frequencies which are sufficiently high ...

IEEE2023

What we look for at Science Robotics

Dario Floreano

AMER ASSOC ADVANCEMENT SCIENCE2022

A Distributed Source Term Estimation Algorithm for Multi-Robot Systems

Alcherio Martinoli, Faezeh Rahbar

Finding sources of airborne chemicals with mobile sensing systems finds applications in safety, security, and emergency situations related to medical, domestic, and environmental domains. Given the often critical nature of all the applications, it is impor ...

IEEE2020

History Repeats Itself: Human Motion Prediction Via Motion Attention

Mathieu Salzmann

Human motion prediction aims to forecast future human poses given a past motion. Whether based on recurrent or feed-forward neural networks, existing methods fail to model the observation that human motion tends to repeat itself, even for complex sports ac ...

Springer Nature2020

A Neuro-Inspired Computational Model for a Visually Guided Robotic Lamprey Using Frame and Event Based Cameras

Auke Ijspeert, Alessandro Crespi, Mehmet Hasan Mutlu, Simon Lukas Hauser, Alexandre Bernardino, Mohammadreza Bayat

The computational load associated with computer vision is often prohibitive, and limits the capacity for on-board image analysis in compact mobile robots. Replicating the kind of feature detection and neural processing that animals excel at remains a chall ...

2020

Automated Taxonomy Induction and its Applications

Amit Gupta

Machine-readable semantic knowledge in the form of taxonomies (i.e., a collection of is-a edges) has proved to be beneficial in an array of NLP tasks including inference, textual entailment, question answering and information extraction. Such widespread ut ...

EPFL2017

LCAV-31: a dataset for light field object recognition

Nelly Julie Afonso, Martin Vetterli, Alireza Ghasemi

We present LCAV-31, a multi-view object recognition dataset designed specifically for benchmarking light field image analysis tasks. The principal distinctive factor of LCAV-31 compared to similar datasets is its design goals and availability of novel visu ...

International Society for Optics and Photonics2014

Towards Dynamic Trot Gait Locomotion—Design, Control and Experiments with Cheetah-cub, a Compliant Quadruped Robot

Auke Ijspeert, Alexander Spröwitz, Massimo Vespignani, Mostafa Ajallooeian, Alexandre Tuleu

We present robot design and results from locomotion experiments with a novel, compliant quadruped robot: Cheetah-cub. The robot's leg configuration is based on a spring-loaded, panthograph-mechanism with multiple segments. A dedicated open-loop, joint-spac ...

2013

Kernel sparse subspace clustering

Jean-Philippe Thiran, Devis Tuia, Frank Grégoire Jean de Morsier

2013

CURVACE - CURVed Artificial Compound Eyes

Dario Floreano, Jean-Christophe Zufferey, Michal Karol Dobrzynski, Ramon Pericet Camara, Géraud L'Eplattenier

CURVACE aims at designing, developing, and assessing CURVed Artificial Compound Eyes, a radically novel family of vision systems. This innovative approach will provide more efficient visual abilities for embedded applications that require motion analysis i ...

Elsevier B.V.2011

BM: An Iterative Method to Learn Stable Non-Linear Dynamical Systems with Gaussian Mixture Models

Aude Billard, Seyed Mohammad Khansari Zadeh

We model the dynamics of non-linear discrete (i.e. point-to- point) robot motions as a time-independent system described by an autonomous dynamical system (DS). We propose an iterative algorithm to estimate the form of the DS through a mixture of Gaussian ...

2010

Feature Harvesting for Tracking-by-Detection

Pascal Fua, François Fleuret, Vincent Lepetit, Mustafa Özuysal

We propose a fast approach to 3D object detection and pose estimation that owes its robustness to a training phase during which the target object slowly moves with respect to the camera. No additional information is provided to the system, save a very roug ...

Springer2006

Spark Assisted Chemical Engraving (SACE) machining – Haptic device for the operator

Hannes Bleuler, Rolf Wüthrich, Ulrich Spälter

2005

Recognition and Reproduction of Gestures using a Probabilistic Framework combining PCA, ICA and HMM

Aude Billard, Sylvain Calinon

This paper explores the issue of recognizing, generalizing and reproducing arbitrary gestures. We aim at extracting a representation that encapsulates only the key aspects of the gesture and discards the variability intrinsic to each person's motion. We co ...

2005