arXiv subjects

Zhengmao He

Publications and source records attributed to Zhengmao He.

10 recordsLinked to original sources

arXiv2026

Two problems of SI-compact spaces

Zhao and Ho use the irreducible open cover family respected with the Scott topology to introduce the SI-compactness. It has been proved that the SI-compactness is strictly stronger than compactness. In this paper, we prove that the product of finitely many SI-compact spaces is always SI-compact which gives a positive answer for the question posed by Zhao and Ho. Furthermore, we show that the category of all SI-compact spaces is not a reflective full subcategory of TOP.

math.GN↗

arXiv2026

A new method for constructing a compact and non SI-compact space

In this paper, we provide a new method for constructing a compact and non SI-compact space and thus give a new answer for the question posed by Zhao and Ho. Using this method, we find a countable compact space which fails to be SI-compact. As a corollary, some new non sober frames are obtained and thus we give a new answer for a question raised by A.Jung. Inspired by the definition of SI-compactness, we introduce a new notion of compactness of topological spaces, namely, v-compactness, which is stronger than SI-compactness.Some properties of v-compactness, SI-compactness and weak v-compactness are discussed. Specifically, we prove that (1) all closed subspaces of a v-compact(SI-compact,weakly v-compact) space are v-compact (SI-compact, weakly v-compact);(2) a characterization of v-compactness for the upper topology is given; (3)some characterizations of weakly v-compact subsets of real line and Sorgenfrey line are given.

math.GN↗

arXiv2026

PAKE: Learning Whole-Body Loco-Manipulation with Partial Kinematic Embeddings

Loco-manipulation has recently shown promising capabilities; however, achieving high-precision control, managing the high-dimensional action space induced by many degrees of freedom (DoFs), and fully exploiting the inherent redundancy of whole-body systems remain challenging. In this paper, we propose a novel whole-body control framework that effectively addresses these challenges by decomposing the complex loco-manipulation problem into partial reference motion generation and low-level imitation control. We introduce a new Kinematic Normalizing Flow (KNF) model, trained on a large-scale kinematic dataset, that generates diverse yet feasible partial reference motions. A high-level controller is then trained to navigate the KNF's latent space to exploit redundant solutions, while a low-level controller ensures physically feasible and accurate motion execution. We validate our approach on the quadrupedal robot equipped with a six-DoF robotic arm. In simulation, experimental results show that our approach significantly outperforms state-of-the-art methods in terms of tracking accuracy and feasible workspace coverage. For hardware deployment, we evaluate the system over 24 episodes across 8 different mobile loco-manipulation tasks. The system achieves end-effector pose-tracking errors of 4.5 cm and 0.14 rad, while maintaining accurate locomotion tracking with linear and angular velocity errors of 0.1 m/s and 0.01 rad/s, respectively, outperforming competitive baselines. Our method represents a practical and powerful solution for accurate and generalized whole-body loco-manipulation in high-DoF robotic systems, with promising potential for diverse downstream robotic tasks.

cs.RO↗

arXiv2026

Learning Dynamic Pick-and-Place for a Legged Manipulator

Legged manipulators extend robotic capabilities beyond static manipulation by integrating agile locomotion with versatile arm control. However, achieving precise manipulation while maintaining coordinated locomotion remains a major challenge. This work presents a hierarchical reinforcement learning framework for dynamic pick-and-place tasks using a quadruped equipped with a 6-DOF robotic arm. The framework incorporates an explicit mass estimation module enabling adaptive whole-body control for objects with varying weights. In simulation, the system achieves an 86.05% success rate with payloads up to 2.3 kg. The approach is further validated through real-world experiments across six representative scenarios with controlled variations in object physical properties (size and mass) and task heights. Specifically, within a wide vertical workspace ranging from ground level to 1.1~m-high tabletops, the system demonstrates an average success rate of 73.3% for payloads up to 1.3 kg, with an average execution time of 4.06 s. Unlike prior works that handle lightweight objects and execute pick-and-place motions with slow, piecewise motions, the proposed framework exploits concurrent locomotion and manipulation for dynamic, continuous execution. These results demonstrate the potential of quadrupedal mobile manipulators for adaptive, whole-body pick-and-place with heavier payloads and extended workspaces.

cs.RO↗

arXiv2026

Closing the Reality Gap: Zero-Shot Sim-to-Real Deployment for Dexterous Force-Based Grasping and Manipulation

Human-like dexterous hands with multiple fingers offer human-level manipulation capabilities, but training control policies that can directly deploy on real hardware remains difficult due to contact-rich physics and imperfect actuation. We close this gap with a practical sim-to-real reinforcement learning (RL) framework that utilizes dense tactile feedback combined with joint torque sensing to explicitly regulate physical interactions. To enable effective sim-to-real transfer, we introduce (i) a computationally fast tactile simulation that computes distances between dense virtual tactile units and the object via parallel forward kinematics, providing high-rate, high-resolution touch signals needed by RL; (ii) a current-to-torque calibration that eliminates the need for torque sensors on dexterous hands by mapping motor current to joint torque; and (iii) actuator dynamics modeling to bridge the actuation gaps with randomization of non-ideal effects such as backlash, torque-speed saturation. Using an asymmetric actor-critic PPO pipeline trained entirely in simulation, our policies deploy directly to a five-finger hand. The resulting policies demonstrated two essential skills: (1) command-based, controllable grasp force tracking, and (2) reorientation of objects in the hand, both of which were robustly executed without fine-tuning on the robot. By combining tactile and torque in the observation space with effective sensing/actuation modeling, our system provides a practical solution to achieve reliable dexterous manipulation. To our knowledge, this is the first demonstration of controllable grasping on a multi-finger dexterous hand trained entirely in simulation and transferred zero-shot on real hardware.

cs.RO↗

arXiv2025

When do weakly first-countable spaces and the Scott topology of open set lattice become sober?

In this paper, we investigate the sobriety of weakly first-countable spaces and give some sufficient conditions that the Scott topologies of the open set lattices are sober. The main results are: (1) Let $P$ and $Q$ be two posets. If $ΣP\times ΣQ$ is a Fréchet space, then $Σ(P\times Q)=ΣP \times ΣQ$. (2) For every $ω$-well-filtered coherent $d$-space $X$, if $X\times X$ is a Fréchet space, then $X$ is sober; (3) For every $ω$ type P-space or consonant Wilker space $X$, $Σ\mathcal{O}(X)$ is sober.

math.GN↗

arXiv2025

ArrayBot: Reinforcement Learning for Generalizable Distributed Manipulation through Touch

We present ArrayBot, a distributed manipulation system consisting of a $16 \times 16$ array of vertically sliding pillars integrated with tactile sensors, which can simultaneously support, perceive, and manipulate the tabletop objects. Towards generalizable distributed manipulation, we leverage reinforcement learning (RL) algorithms for the automatic discovery of control policies. In the face of the massively redundant actions, we propose to reshape the action space by considering the spatially local action patch and the low-frequency actions in the frequency domain. With this reshaped action space, we train RL agents that can relocate diverse objects through tactile observations only. Surprisingly, we find that the discovered policy can not only generalize to unseen object shapes in the simulator but also transfer to the physical robot without any domain randomization. Leveraging the deployed policy, we present abundant real-world manipulation tasks, illustrating the vast potential of RL on ArrayBot for distributed manipulation.

cs.RO↗

arXiv2024

Learning Visual Quadrupedal Loco-Manipulation from Demonstrations

Quadruped robots are progressively being integrated into human environments. Despite the growing locomotion capabilities of quadrupedal robots, their interaction with objects in realistic scenes is still limited. While additional robotic arms on quadrupedal robots enable manipulating objects, they are sometimes redundant given that a quadruped robot is essentially a mobile unit equipped with four limbs, each possessing 3 degrees of freedom (DoFs). Hence, we aim to empower a quadruped robot to execute real-world manipulation tasks using only its legs. We decompose the loco-manipulation process into a low-level reinforcement learning (RL)-based controller and a high-level Behavior Cloning (BC)-based planner. By parameterizing the manipulation trajectory, we synchronize the efforts of the upper and lower layers, thereby leveraging the advantages of both RL and BC. Our approach is validated through simulations and real-world experiments, demonstrating the robot's ability to perform tasks that demand mobility and high precision, such as lifting a basket from the ground while moving, closing a dishwasher, pressing a button, and pushing a door. Project website: https://zhengmaohe.github.io/leg-manip

cs.RO↗

arXiv2024

Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization

Combining offline and online reinforcement learning (RL) is crucial for efficient and safe learning. However, previous approaches treat offline and online learning as separate procedures, resulting in redundant designs and limited performance. We ask: Can we achieve straightforward yet effective offline and online learning without introducing extra conservatism or regularization? In this study, we propose Uni-o4, which utilizes an on-policy objective for both offline and online learning. Owning to the alignment of objectives in two phases, the RL agent can transfer between offline and online learning seamlessly. This property enhances the flexibility of the learning paradigm, allowing for arbitrary combinations of pretraining, fine-tuning, offline, and online learning. In the offline phase, specifically, Uni-o4 leverages diverse ensemble policies to address the mismatch issues between the estimated behavior policy and the offline dataset. Through a simple offline policy evaluation (OPE) approach, Uni-o4 can achieve multi-step policy improvement safely. We demonstrate that by employing the method above, the fusion of these two paradigms can yield superior offline initialization as well as stable and rapid online fine-tuning capabilities. Through real-world robot tasks, we highlight the benefits of this paradigm for rapid deployment in challenging, previously unseen real-world environments. Additionally, through comprehensive evaluations using numerous simulated benchmarks, we substantiate that our method achieves state-of-the-art performance in both offline and offline-to-online fine-tuning learning. Our website: https://lei-kun.github.io/uni-o4/ .

cs.LG↗

arXiv2022

Some problems about co-consonance of topological spaces

In this paper, we first prove that the retract of a consonant space (or co-consonant space) is consonant (co-consonant). Using this result, some related results have obtained. Simultaneously, we proved that (1) the co-consonance of the Smyth powerspace implies the co-consonance of a topological space under a necessary condition; (2) the co-consonance of a topological implies the co-consonance of the smyth powerspace under some conditions; (3) if the lower powerspace is co-consonant, then the topological space is co-consonant; (4) the co-consonance of implies the co-consonance of the lower powerspace with some sufficient conditions.

cs.LO↗