collaborators

8 papers

cs.LG20262 cited

Embedded Inter-Subject Variability in Adversarial Learning for Inertial Sensor-Based Human Activity Recognition

Francisco M. Calatrava-Nicolás, Shoko Miyauchi, Vitor Fortes Rey +3

This paper addresses the problem of Human Activity Recognition (HAR) using data from wearable inertial sensors. An important challenge in HAR is the model's generalization capabili…

cs.RO2025

Single-View Shape Completion for Robotic Grasping in Clutter

Abhishek Kashyap, Yuxuan Yang, Henrik Andreasson +1

In vision-based robot manipulation, a single camera view can only capture one side of objects of interest, with additional occlusions in cluttered scenes further restricting visibi…

cs.RO2025

Can Context Bridge the Reality Gap? Sim-to-Real Transfer of Context-Aware Policies

Marco Iannotta, Yuxuan Yang, Johannes A. Stork +2

Sim-to-real transfer remains a major challenge in reinforcement learning (RL) for robotics, as policies trained in simulation often fail to generalize to the real world due to disc…

cs.LG2025

KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies

Shih-Min Yang, Martin Magnusson, Johannes A. Stork +1

Soft Actor-Critic (SAC) has achieved notable success in continuous control tasks but struggles in sparse reward settings, where infrequent rewards make efficient exploration challe…

cs.RO2025

Exploiting Radiance Fields for Grasp Generation on Novel Synthetic Views

Abhishek Kashyap, Henrik Andreasson, Todor Stoyanov

Vision based robot manipulation uses cameras to capture one or more images of a scene containing the objects to be manipulated. Taking multiple images can help if any object is occ…

cs.RO2025

Beyond Predefined Actions: Integrating Behavior Trees and Dynamic Movement Primitives for Robot Learning from Demonstration

David Cáceres Domínguez, Erik Schaffernicht, Todor Stoyanov

Interpretable policy representations like Behavior Trees (BTs) and Dynamic Motion Primitives (DMPs) enable robot skill transfer from human demonstrations, but each faces limitation…