12 papers
Autonomous Obstacle Removal for Excavators through Policy Learning with Particle Simulation
Yuki Kadokawa, Sandro M. Alcantara Tacora, Taro Abe +4
Autonomous obstacle removal from the ground is an important earthwork task, but this is difficult to automate because an excavator must adapt its excavation trajectories over repea…
Bridged SBI: Correcting Biased Low-Fidelity Posteriors for Cost-Efficient High-Fidelity Inference
Gahee Kim, Yuki Kadokawa, Sandro M. Alcantara Tacora +5
Accurate calibration of particle-based simulators is crucial for robotic earthwork simulation, but analytical calibration is challenging due to this task's highly nonlinear particl…
ViSA: Visited-State Augmentation for Generalized Goal-Space Contrastive Reinforcement Learning
Issa Nakamura, Tomoya Yamanokuchi, Yuki Kadokawa +5
Goal-Conditioned Reinforcement Learning (GCRL) is a framework for learning a policy that can reach arbitrarily given goals. In particular, Contrastive Reinforcement Learning (CRL)…
Robust Sim-to-Real Cloth Untangling through Reduced-Resolution Observations via Adaptive Force-Difference Quantization
Yoshihisa Tsurumine, Yuki Kadokawa, Kohei Hayashi +2
Robotic cloth untangling requires progressively disentangling fabric by adapting pulling actions to changing contact and tension conditions. Because large-scale real-world training…
DeReCo: Decoupling Representation and Coordination Learning for Object-Adaptive Decentralized Multi-Robot Cooperative Grasping and Lifting
Kazuki Shibata, Ryosuke Sota, Shandil Dhiresh Bosch +3
Generalizing decentralized multi-robot cooperative grasping and lifting across objects with diverse shapes and physical properties remains a fundamental challenge. Under decentrali…
Prolonging Tool Life: Learning Skillful Use of General-purpose Tools through Lifespan-guided Reinforcement Learning
Po-Yen Wu, Cheng-Yu Kuo, Yuki Kadokawa +1
In inaccessible environments with uncertain task demands, robots often rely on general-purpose tools that lack predefined usage strategies. These tools are not tailored for particu…
DAPPER: Discriminability-Aware Policy-to-Policy Preference-Based Reinforcement Learning for Query-Efficient Robot Skill Acquisition
Yuki Kadokawa, Jonas Frey, Takahiro Miki +2
Preference-based Reinforcement Learning (PbRL) enables policy learning through simple queries comparing trajectories from a single policy. While human responses to these queries ma…
Learning Quiet Walking for a Small Home Robot
Ryo Watanabe, Takahiro Miki, Fan Shi +5
As home robotics gains traction, robots are increasingly integrated into households, offering companionship and assistance. Quadruped robots, particularly those resembling dogs, ha…
Progressive-Resolution Policy Distillation: Leveraging Coarse-Resolution Simulations for Time-Efficient Fine-Resolution Policy Learning
Yuki Kadokawa, Hirotaka Tahara, Takamitsu Matsubara
In earthwork and construction, excavators often encounter large rocks mixed with various soil conditions, requiring skilled operators. This paper presents a framework for achieving…
Robust Iterative Value Conversion: Deep Reinforcement Learning for Neurochip-driven Edge Robots
Yuki Kadokawa, Tomohito Kodera, Yoshihisa Tsurumine +2
A neurochip is a device that reproduces the signal processing mechanisms of brain neurons and calculates Spiking Neural Networks (SNNs) with low power consumption and at high speed…
Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomization
Yuki Kadokawa, Lingwei Zhu, Yoshihisa Tsurumine +1
Deep reinforcement learning with domain randomization learns a control policy in various simulations with randomized physical and sensor model parameters to become transferable to…
Binarized P-Network: Deep Reinforcement Learning of Robot Control from Raw Images on FPGA
Yuki Kadokawa, Yoshihisa Tsurumine, Takamitsu Matsubara
This paper explores a Deep Reinforcement Learning (DRL) approach for designing image-based control for edge robots to be implemented on Field Programmable Gate Arrays (FPGAs). Alth…