跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1680新增论文
+1333其中 AI 相关
+187已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-17 23:35各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 10:35 — 2026-11-18 10:35(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-18 04:28最近发现新增版本:2026-11-17 23:35库内论文最新更新时间:2026-11-17 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

25,786 已收录论文21,491 AI 相关7,725 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 3 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v2arXiv:2603.04760

Designing and Validating a Self-Aligning Tool Changer for Modular Reconfigurable Manipulation Robots

Mahfudz Maskur, Takuya Kiyokawa, Kensuke Harada

原文摘要

Modular reconfigurable robots require reliable mechanisms for automated tool exchange, but conventional rigid active couplings often fail due to inevitable positioning and orientational errors. To address this, we propose a misalignment-tolerant tool changer. The tool changer consists of an insert part on the robot side, which contains a servo-driven cam and lock-pin, and a receptacle part on the tool side, which has an isosceles triangular lead-in guide and chamfered walls. During insertion, these geometries generate angled contact forces that passively align the two parts, so the tool changer compensates for angular and lateral misalignments without force sensors. A motor-driven rotating tool exchange station stores the tools and rotates to bring the selected tool to the exchange position. Experiments confirmed that, with the current guide and chamfer geometry, the tool changer tolerates rotational offsets of $ \pm$ 20 degrees and lateral offsets of up to 7 mm.

cs.RO

版本更新 · v2arXiv:2603.04757

Gait Generation Balancing Joint Load and Mobility for Legged Modular Robots with Easily Detachable Joints

Kennosuke Chihara, Takuya Kiyokawa, Tetsuya Shitara, Kensuke Harada

原文摘要

Modular robots can adapt their morphology to diverse tasks, but locomotion can impose large loads on detachable joints. This paper presents an NSGA-III-based multi-objective gait optimization framework with three objectives: a locomotion speed, a static stability, and a normalized joint-load metric based on joint reaction forces. The framework yields nondominated gait candidates that reveal the trade-offs among these objectives. In a flat-terrain comparison using the 6-legged tetrapod gait, adding the joint-load objective reduced the mean maximum joint reaction force by 11.5% and increased the mean minimum stability by 41.2%, while decreasing the mean forward speed by 10.5%. Simulations under flat, slope, and step conditions showed that locomotion feasibility depended on the combination of robot configuration, gait, and terrain. In physical experiments, the 4-legged trot completed locomotion on flat terrain and a 10 degrees slope, whereas the 6-legged tetrapod and tripod completed locomotion on flat terrain. These results demonstrate the feasibility of joint-load-aware gait generation based on explicit trade-offs among the three evaluated quantities

cs.RO

新论文 · v1arXiv:2610.38513

Force-Driven Hook Disassembly via Constraint-Aware Object-Centric Reinforcement Learning

Nadeen Elhadad, Takuya Kiyokawa, Kensuke Harada

原文摘要

The growing volume of end-of-life products has intensified the need for automated disassembly, yet hook-type connections remain challengin: their orientations vary, they deform under load, and their geometry is hidden, so vision alone cannot identify a feasible non-destructive disassembly direction. This work proposes a constraint-aware reinforcement learning framework that infers feasible extraction directions online from contact forces. The policy is trained in a robot-agnostic, object-centric simulation on a simplified peg-in-hole pair and deployed zero-shot on a physical robot, where it transfers to real connections with unseen, multi-stage constraint structures. Because instantaneous contact forces are noisy and locally ambiguous, the policy is coupled with a particle filter belief that provides the policy with temporally integrated directional information and reduces redundant exploratory motion. The approach is validated on four real-world tasks, from peg-in-hole pairs to the inner propeller and front cover of an end-of-life air-conditioning unit. The full method achieves success rates of 100%, 100%, 90%, and 75% with the highest path efficiency on every task, and raises the success rate on the air-conditioning cover from 45% to 75% relative to a policy trained without the belief. These results indicate that force-driven reinforcement learning can enable disassembly without product-specific models or demonstrations.

cs.RO