Search Results for author: Ville Kyrki

Found 34 papers, 16 papers with code

Co-Imitation: Learning Design and Behaviour by Imitation

no code implementations2 Sep 2022 Chang Rajani, Karol Arndt, David Blanco-Mulero, Kevin Sebastian Luck, Ville Kyrki

To this end we propose a co-imitation methodology for adapting behaviour and morphology by matching state distributions of the demonstrator.

Imitation Learning

Generating people flow from architecture of real unseen environments

1 code implementation23 Aug 2022 Francesco Verdoja, Tomasz Piotr Kucner, Ville Kyrki

In this work we propose a novel approach to learn people dynamics from geometry, where a model is trained and evaluated on real human trajectories in large-scale environments.

Online vs. Offline Adaptive Domain Randomization Benchmark

1 code implementation29 Jun 2022 Gabriele Tiboni, Karol Arndt, Giuseppe Averta, Ville Kyrki, Tatiana Tommasi

However, transferring the acquired knowledge to the real world can be challenging due to the reality gap.

Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models

no code implementations18 Apr 2022 Ali Ghadirzadeh, Petra Poklukar, Karol Arndt, Chelsea Finn, Ville Kyrki, Danica Kragic, Mårten Björkman

We present a data-efficient framework for solving sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models.

Decision Making reinforcement-learning +1

A Safety-Critical Decision Making and Control Framework Combining Machine Learning and Rule-based Algorithms

no code implementations30 Jan 2022 Andrei Aksjonov, Ville Kyrki

Yet, the latter cannot compete with the first ones in robustness to multiple requirements, for instance, simultaneously addressing safety, comfort, and efficiency.

Autonomous Driving Decision Making

SafeAPT: Safe Simulation-to-Real Robot Learning using Diverse Policies Learned in Simulation

1 code implementation27 Jan 2022 Rituraj Kaushik, Karol Arndt, Ville Kyrki

In this work, we introduce a novel learning algorithm called SafeAPT that leverages a diverse repertoire of policies evolved in the simulation and transfers the most promising safe policy to the real robot through episodic interaction.

DROPO: Sim-to-Real Transfer with Offline Domain Randomization

1 code implementation20 Jan 2022 Gabriele Tiboni, Karol Arndt, Ville Kyrki

In recent years, domain randomization has gained a lot of traction as a method for sim-to-real transfer of reinforcement learning policies in robotic manipulation; however, finding optimal randomization distributions can be difficult.

reinforcement-learning

Manipulation of Granular Materials by Learning Particle Interactions

1 code implementation3 Nov 2021 Neea Tuomainen, David Blanco-Mulero, Ville Kyrki

In this paper, we propose to use a graph-based representation to model the interaction dynamics of the material and rigid bodies manipulating it.

Vision Transformer for Learning Driving Policies in Complex Multi-Agent Environments

no code implementations14 Sep 2021 Eshagh Kargar, Ville Kyrki

Driving in a complex urban environment is a difficult task that requires a complex decision policy.

MACRPO: Multi-Agent Cooperative Recurrent Policy Optimization

1 code implementation2 Sep 2021 Eshagh Kargar, Ville Kyrki

We propose two novel ways of integrating information across agents and time in MACRPO: First, we use a recurrent layer in critic's network architecture and propose a new framework to use a meta-trajectory to train the recurrent layer.

Evolving-Graph Gaussian Processes

1 code implementation29 Jun 2021 David Blanco-Mulero, Markus Heinonen, Ville Kyrki

Graph Gaussian Processes (GGPs) provide a data-efficient solution on graph structured domains.

Gaussian Processes Time Series Regression

Affine Transport for Sim-to-Real Domain Adaptation

no code implementations25 May 2021 Anton Mallasto, Karol Arndt, Markus Heinonen, Samuel Kaski, Ville Kyrki

In this paper, we present affine transport -- a variant of optimal transport, which models the mapping between state transition distributions between the source and target domains with an affine transformation.

Domain Adaptation OpenAI Gym

Increasing the Efficiency of Policy Learning for Autonomous Vehicles by Multi-Task Representation Learning

no code implementations26 Mar 2021 Eshagh Kargar, Ville Kyrki

To do this, we train an encoder-decoder deep neural network to predict multiple application-relevant factors such as the trajectories of other agents and the ego car.

Autonomous Vehicles Decision Making +2

Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation

no code implementations12 Mar 2021 Karol Arndt, Oliver Struckmeier, Ville Kyrki

Domain adaptation is a common problem in robotics, with applications such as transferring policies from simulation to real world and lifelong learning.

Domain Adaptation

DDGC: Generative Deep Dexterous Grasping in Clutter

no code implementations8 Mar 2021 Jens Lundell, Francesco Verdoja, Ville Kyrki

Multi-finger grasping in cluttered scenes, on the other hand, remains mostly unexplored due to the added difficulty of reasoning over obstacles which greatly increases the computational time to generate high-quality collision-free grasps.

Robotic Grasping

Multi-FinGAN: Generative Coarse-To-Fine Sampling of Multi-Finger Grasps

1 code implementation17 Dec 2020 Jens Lundell, Enric Corona, Tran Nguyen Le, Francesco Verdoja, Philippe Weinzaepfel, Gregory Rogez, Francesc Moreno-Noguer, Ville Kyrki

While there exists many methods for manipulating rigid objects with parallel-jaw grippers, grasping with multi-finger robotic hands remains a quite unexplored research topic.

Autoencoding Slow Representations for Semi-supervised Data Efficient Regression

no code implementations11 Dec 2020 Oliver Struckmeier, Kshitij Tiwari, Ville Kyrki

We find that slow representations lead to equal or better downstream task performance and data efficiency in different experiment domains when compared to representations without slowness regularization.

Representation Learning

Probabilistic Surface Friction Estimation Based on Visual and Haptic Measurements

no code implementations16 Oct 2020 Tran Nguyen Le, Francesco Verdoja, Fares J. Abu-Dakka, Ville Kyrki

Accurately modeling local surface properties of objects is crucial to many robotic applications, from grasping to material recognition.

Material Recognition

Few-shot model-based adaptation in noisy conditions

no code implementations16 Oct 2020 Karol Arndt, Ali Ghadirzadeh, Murtaza Hazara, Ville Kyrki

Few-shot adaptation is a challenging problem in the context of simulation-to-real transfer in robotics, requiring safe and informative data collection.

reinforcement-learning

Notes on the Behavior of MC Dropout

1 code implementation6 Aug 2020 Francesco Verdoja, Ville Kyrki

Among the various options to estimate uncertainty in deep neural networks, Monte-Carlo dropout is widely popular for its simplicity and effectiveness.

Data-efficient visuomotor policy training using reinforcement learning and generative models

no code implementations26 Jul 2020 Ali Ghadirzadeh, Petra Poklukar, Ville Kyrki, Danica Kragic, Mårten Björkman

We present a data-efficient framework for solving visuomotor sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models.

Decision Making Disentanglement +2

DeFINE: Delayed Feedback based Immersive Navigation Environment for Studying Goal-Directed Human Navigation

1 code implementation6 Mar 2020 Kshitij Tiwari, Ville Kyrki, Allen Cheung, Naohide Yamamoto

With the advent of consumer-grade products for presenting an immersive virtual environment (VE), there is a growing interest in utilizing VEs for testing human navigation behavior.

Efficient Latent Representations using Multiple Tasks for Autonomous Driving

no code implementations2 Mar 2020 Eshagh Kargar, Ville Kyrki

Driving in the dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision policy.

Robotics

Meta Reinforcement Learning for Sim-to-real Domain Adaptation

no code implementations16 Sep 2019 Karol Arndt, Murtaza Hazara, Ali Ghadirzadeh, Ville Kyrki

Modern reinforcement learning methods suffer from low sample efficiency and unsafe exploration, making it infeasible to train robotic policies entirely on real hardware.

Domain Adaptation Meta-Learning +2

MuPNet: Multi-modal Predictive Coding Network for Place Recognition by Unsupervised Learning of Joint Visuo-Tactile Latent Representations

no code implementations16 Sep 2019 Oliver Struckmeier, Kshitij Tiwari, Shirin Dora, Martin J. Pearson, Sander M. Bohte, Cyriel MA Pennartz, Ville Kyrki

Extracting and binding salient information from different sensory modalities to determine common features in the environment is a significant challenge in robotics.

Beyond Top-Grasps Through Scene Completion

no code implementations15 Sep 2019 Jens Lundell, Francesco Verdoja, Ville Kyrki

Current end-to-end grasp planning methods propose grasps in the order of seconds that attain high grasp success rates on a diverse set of objects, but often by constraining the workspace to top-grasps.

Grasp Generation

ViTa-SLAM: A Bio-inspired Visuo-Tactile SLAM for Navigation while Interacting with Aliased Environments

no code implementations14 Jun 2019 Oliver Struckmeier, Kshitij Tiwari, Mohammed Salman, Martin J. Pearson, Ville Kyrki

RatSLAM is a rat hippocampus-inspired visual Simultaneous Localization and Mapping (SLAM) framework capable of generating semi-metric topological representations of indoor and outdoor environments.

Robotics

Object Pose Estimation in Robotics Revisited

no code implementations6 Jun 2019 Antti Hietanen, Jyrki Latokartano, Alessandro Foi, Roel Pieters, Ville Kyrki, Minna Lanz, Joni-Kristian Kämäräinen

The evaluation metric is based on non-parametric probability density that is estimated from samples of a real physical setup.

3D Pose Estimation 6D Pose Estimation +1

From Video Game to Real Robot: The Transfer between Action Spaces

1 code implementation2 May 2019 Janne Karttunen, Anssi Kanervisto, Ville Kyrki, Ville Hautamäki

Deep reinforcement learning has proven to be successful for learning tasks in simulated environments, but applying same techniques for robots in real-world domain is more challenging, as they require hours of training.

Transfer Learning

Affordance Learning for End-to-End Visuomotor Robot Control

2 code implementations10 Mar 2019 Aleksi Hämäläinen, Karol Arndt, Ali Ghadirzadeh, Ville Kyrki

Training end-to-end deep robot policies requires a lot of domain-, task-, and hardware-specific data, which is often costly to provide.

Robust Grasp Planning Over Uncertain Shape Completions

2 code implementations2 Mar 2019 Jens Lundell, Francesco Verdoja, Ville Kyrki

We present a method for planning robust grasps over uncertain shape completed objects.

Robotics

Deep Network Uncertainty Maps for Indoor Navigation

1 code implementation13 Sep 2018 Francesco Verdoja, Jens Lundell, Ville Kyrki

Most mobile robots for indoor use rely on 2D laser scanners for localization, mapping and navigation.

Autonomous Navigation

Hallucinating robots: Inferring Obstacle Distances from Partial Laser Measurements

1 code implementation31 May 2018 Jens Lundell, Francesco Verdoja, Ville Kyrki

However, those sensors are unable to correctly provide distance to obstacles such as glass panels and tables whose actual occupancy is invisible at the height the sensor is measuring.

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