Search Results for author: Jens Kober

Found 22 papers, 8 papers with code

Robust Multi-Modal Density Estimation

no code implementations19 Jan 2024 Anna Mészáros, Julian F. Schumann, Javier Alonso-Mora, Arkady Zgonnikov, Jens Kober

Development of multi-modal, probabilistic prediction models has lead to a need for comprehensive evaluation metrics.

Density Estimation

Predictable Reinforcement Learning Dynamics through Entropy Rate Minimization

1 code implementation30 Nov 2023 Daniel Jarne Ornia, Giannis Delimpaltadakis, Jens Kober, Javier Alonso-Mora

In Reinforcement Learning (RL), agents have no incentive to exhibit predictable behaviors, and are often pushed (through e. g. policy entropy regularization) to randomize their actions in favor of exploration.

Policy Gradient Methods reinforcement-learning +1

Using Models Based on Cognitive Theory to Predict Human Behavior in Traffic: A Case Study

no code implementations24 May 2023 Julian F. Schumann, Aravinda Ramakrishnan Srinivasan, Jens Kober, Gustav Markkula, Arkady Zgonnikov

The development of automated vehicles has the potential to revolutionize transportation, but they are currently unable to ensure a safe and time-efficient driving style.

Decision Making

Robotic Packaging Optimization with Reinforcement Learning

no code implementations26 Mar 2023 Eveline Drijver, Rodrigo Pérez-Dattari, Jens Kober, Cosimo Della Santina, Zlatan Ajanović

Intelligent manufacturing is becoming increasingly important due to the growing demand for maximizing productivity and flexibility while minimizing waste and lead times.


Robotic Fabric Flattening with Wrinkle Direction Detection

no code implementations8 Mar 2023 Yulei Qiu, Jihong Zhu, Cosimo Della Santina, Michael Gienger, Jens Kober

Deformable Object Manipulation (DOM) is an important field of research as it contributes to practical tasks such as automatic cloth handling, cable routing, surgical operation, etc.

Deformable Object Manipulation

PARTNR: Pick and place Ambiguity Resolving by Trustworthy iNteractive leaRning

no code implementations15 Nov 2022 Jelle Luijkx, Zlatan Ajanovic, Laura Ferranti, Jens Kober

We extend previous works and present the PARTNR algorithm that can detect ambiguities in the trained policy by analyzing multiple modalities in the pick and place poses using topological analysis.

Benchmark for Models Predicting Human Behavior in Gap Acceptance Scenarios

no code implementations10 Nov 2022 Julian Frederik Schumann, Jens Kober, Arkady Zgonnikov

Autonomous vehicles currently suffer from a time-inefficient driving style caused by uncertainty about human behavior in traffic interactions.

Autonomous Vehicles Trajectory Planning

Learning to Exploit Elastic Actuators for Quadruped Locomotion

no code implementations15 Sep 2022 Antonin Raffin, Daniel Seidel, Jens Kober, Alin Albu-Schäffer, João Silvério, Freek Stulp

Spring-based actuators in legged locomotion provide energy-efficiency and improved performance, but increase the difficulty of controller design.

Learning to Pick at Non-Zero-Velocity from Interactive Demonstrations

1 code implementation9 Oct 2021 Anna Mészáros, Giovanni Franzese, Jens Kober

This work investigates how the intricate task of a continuous pick & place (P&P) motion may be learned from humans based on demonstrations and corrections.

Gaussian Processes

ILoSA: Interactive Learning of Stiffness and Attractors

1 code implementation4 Mar 2021 Giovanni Franzese, Anna Mészáros, Luka Peternel, Jens Kober

Teaching robots how to apply forces according to our preferences is still an open challenge that has to be tackled from multiple engineering perspectives.

Gaussian Processes

GEM: Glare or Gloom, I Can Still See You -- End-to-End Multimodal Object Detection

no code implementations24 Feb 2021 Osama Mazhar, Robert Babuska, Jens Kober

We additionally record a new RGB-Infra indoor dataset, namely L515-Indoors, and demonstrate that the proposed object detection methodologies are highly effective for a variety of lighting conditions.

Object object-detection +1

Random Shadows and Highlights: A new data augmentation method for extreme lighting conditions

1 code implementation13 Jan 2021 Osama Mazhar, Jens Kober

In this paper, we propose a new data augmentation method, Random Shadows and Highlights (RSH) to acquire robustness against lighting perturbations.

Data Augmentation

DeepKoCo: Efficient latent planning with a task-relevant Koopman representation

no code implementations25 Nov 2020 Bas van der Heijden, Laura Ferranti, Jens Kober, Robert Babuska

This paper presents DeepKoCo, a novel model-based agent that learns a latent Koopman representation from images.

Model Predictive Control

Interactive Imitation Learning in State-Space

1 code implementation2 Aug 2020 Snehal Jauhri, Carlos Celemin, Jens Kober

Imitation Learning techniques enable programming the behavior of agents through demonstrations rather than manual engineering.

Imitation Learning

Smooth Exploration for Robotic Reinforcement Learning

4 code implementations12 May 2020 Antonin Raffin, Jens Kober, Freek Stulp

We evaluate gSDE both in simulation, on PyBullet continuous control tasks, and directly on three different real robots: a tendon-driven elastic robot, a quadruped and an RC car.

Continuous Control reinforcement-learning +1

Deep Reinforcement Learning with Feedback-based Exploration

2 code implementations14 Mar 2019 Jan Scholten, Daan Wout, Carlos Celemin, Jens Kober

We employ binary corrective feedback as a general and intuitive manner to incorporate human intuition and domain knowledge in model-free machine learning.

Continuous Control OpenAI Gym +2

Learning Gaussian Policies from Corrective Human Feedback

no code implementations12 Mar 2019 Daan Wout, Jan Scholten, Carlos Celemin, Jens Kober

We demonstrate that the novel algorithm outperforms the current state-of-the-art in final performance, convergence rate and robustness to erroneous feedback in OpenAI Gym continuous control benchmarks, both for simulated and real human teachers.

Continuous Control Gaussian Processes +1

Interactive Learning with Corrective Feedback for Policies based on Deep Neural Networks

1 code implementation30 Sep 2018 Rodrigo Pérez-Dattari, Carlos Celemin, Javier Ruiz-del-Solar, Jens Kober

Deep Reinforcement Learning (DRL) has become a powerful strategy to solve complex decision making problems based on Deep Neural Networks (DNNs).

Car Racing Decision Making

Using Bayesian Dynamical Systems for Motion Template Libraries

no code implementations NeurIPS 2008 Silvia Chiappa, Jens Kober, Jan R. Peters

Motor primitives or motion templates have become an important concept for both modeling human motor control as well as generating robot behaviors using imitation learning.

Imitation Learning Time Series +1

Policy Search for Motor Primitives in Robotics

no code implementations NeurIPS 2008 Jens Kober, Jan R. Peters

We compare this algorithm to alternative parametrized policy search methods and show that it outperforms previous methods.

Imitation Learning Policy Gradient Methods +2

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