activity
20242026
collaborators

6 papers

cs.RO2026

Orienteering Problem with Uncertain Time-Varying Rewards: Framework and Benchmark for Everyday Service Robotics

Masafumi Endo, Kohei Honda, Yuu Jinnai +1

We present the orienteering problem with uncertain time-varying rewards (OP-UTVR), a novel variant of the orienteering problem (OP). While most existing OP formulations assume rewa…

cs.RO2026

Adaptive Undulatory Locomotion of Snake-like Robots in Dynamic Viscous Environments via Deep Reinforcement Learning

Tsuyoshi Kimoto, Akio Yamano, Kohei Honda +1

This paper demonstrates how deep reinforcement learning (DRL) enables adaptive locomotion of snake-like robots in dynamically changing viscous environments, overcoming the inherent…

cs.RO2026

Reset-Free Reinforcement Learning for Real-World Agile Driving: An Empirical Study

Kohei Honda, Hirotaka Hosogaya

This paper presents an empirical study of reset-free reinforcement learning (RL) for real-world agile driving, in which a physical 1/10-scale vehicle learns continuously on a slipp…

cs.RO2025

DRPA-MPPI: Dynamic Repulsive Potential Augmented MPPI for Reactive Navigation in Unstructured Environments

Takahiro Fuke, Masafumi Endo, Kohei Honda +1

Reactive mobile robot navigation in unstructured environments is challenging when robots encounter unexpected obstacles that invalidate previously planned trajectories. Model predi…

cs.RO2025

Ground and Flight Locomotion for Two-Wheeled Drones via Model Predictive Path Integral Control

Gosuke Kojima, Kohei Honda, Satoshi Nakano +1

This paper presents a novel approach to motion planning for two-wheeled drones that can drive on the ground and fly in the air. Conventional methods for two-wheeled drone motion pl…

cs.RO2024

Towards Local Minima-free Robotic Navigation: Model Predictive Path Integral Control via Repulsive Potential Augmentation

Takahiro Fuke, Masafumi Endo, Kohei Honda +1

Model-based control is a crucial component of robotic navigation. However, it often struggles with entrapment in local minima due to its inherent nature as a finite, myopic optimiz…