arXiv subjects

Lijun Zhu

Publications and source records attributed to Lijun Zhu.

At least 19 recordsLinked to original sources

arXiv2026

Initialization-free ultralow-power programmable spin-orbit torque logic devices enabled by chirally asymmetric switching

Spin logic is of great interest for the development of high-performance, non-Von Neumann artificial intelligence chips. Of particular advantage is the programmable spin-orbit torque logic that can achieve the complete set of the 16 Boolean logic operations within a single device in an initialization-free, low-power, and scalable manner, which is, however, a challenge despite remarkable efforts over more than two decades. Here, utilizing chirally asymmetric switching, we demonstrate an initialization-free, low-power, programmable spin-orbit torque logic device that is capable of the complete set of 16 Boolean logic operations within a single device with only three inputs and ultralow power of < 1 fJ/bit. We also propose the first initialization-free, all-electrical spin-based cascading computing devices, including a half adder, a three-level full adder, a two-level full adder, and a Transfer/NOT selector. These compact and scalable computing devices are enabled by the chirally asymmetric spin-orbit torque switching of a Ta/FeCoB bilayer with a significant perpendicular Dzyaloshinskii-Moriya interaction field. These results pave an intriguing way for the development of next-generation high-performance large-scale in-memory computing chips based on chirally asymmetric spin-orbit torque switching.

cond-mat.mtrl-sci↗

arXiv2026

Demonstration of room-temperature, magnetic-field-free, and ultralow-power spin-orbit torque logic device based on composition-uniform van der Waals magnet Fe3GaTe2

Van der Waals magnets have received blooming interest in material science and spintronics for the advantages of low magnetization, flexible stacking, strong tunability, and dangling-bond-free interfaces. However, there has been no report of room-temperature magnetic-field-free spin logic device based on a van der Waals magnet. Here, we demonstrate a room-temperature, field-free, low-power, scalable spin-orbit torque in-memory computing logic device utilizing a van der Waals magnet Fe3GaTe2 bit with strong perpendicular magnetic anisotropy and a Pt channel with strong spin Hall effect, high electrical conductivity, and electric asymmetries. Current pulse width-dependent switching measurement reveals a low intrinsic critical magnetic-field-free switching current of 1.8e7 A cm-2, a high thermal stability factor of 50, and the potential of an ultralow write power of 1.5 fJ per bit at 1 ns pulse width for a typical industrial-level device dimensions (40 times lower than the industrially optimized W/FeCoB device). These results suggest a great potential of van der Waals magnets in dense, ultralow-power, scalable in-memory computing technologies.

cond-mat.mtrl-sci↗

arXiv2026

RAEM: Robust Autonomous Exploration for Multi-Floor Environments with a Quadruped Robot

In this paper, we propose RAEM, a robust autonomous exploration framework for quadruped robots operating in multi-floor environments. Most existing ground-robot exploration approaches rely on planar traversability representations, which cannot adequately represent the overlapping structures and cross-floor connectivity of multi-floor buildings. Although tomography-based representations provide effective traversability modeling for multi-floor navigation, maintaining a global tomography map incurs substantial computational overhead for online exploration with frequent replanning. Moreover, sparse and fragmented LiDAR observations in stairwells can degrade local traversability estimation, leading to irregular viewpoint placement and temporary topological disconnections. To address these challenges, RAEM adopts a hybrid local-global traversability representation, in which a local tomography map and an explicitly categorized local 3D grid map are used for online terrain analysis and connectivity evaluation, while an elevation-aware global topological graph is incrementally constructed from these local spatial representations for efficient cross-floor exploration planning. We further introduce a staircase center alignment strategy to reduce abrupt yaw variations during climbing and a dual path searching mechanism to recover guidance paths when the global topology is locally disconnected. Extensive simulation and real-world experiments demonstrate robust and computationally stable autonomous exploration across multi-floor structures, including continuous exploration of a five-floor stairwell.

cs.RO↗

arXiv2026

Dominant spin Hall torque and negligible orbital Hall torque in α-W/ferromagnet heterostructures with artifacts-free angular momentum detectors

α-phased W was theoretically predicted to have a negative spin Hall conductivity and a positive orbital Hall conductivity at the same time, leaving the physical origin of the current-induced torque a critical open question. Here, we develop two angular momentum detectors of Cu/Ni/Cu and Cu/Fe60Co20B20/Cu that are free of artifacts torques (e.g., self-induced torque and spin-vorticity torque) and clarify that the spin-orbit torque contributed by α-W remains negative and predominantly from the spin Hall effect in the entire thickness regime. The damping-like torque exhibits a monotonic decay as the W thickness increases above 5 nm likely due to the thickness-dependent structural evolution and resistivity reduction of the W layer. The negative torque in the entire thickness regime suggests negligible orbital Hall torque from α-W. This result is consistent with the theory that the orbital Hall effect from simplified band structure calculations is not a non-local angular momentum source.

cond-mat.mes-hall↗

arXiv2026

Universal scaling of the Anomalous Hall voltage of magnetic layer with the adjacent conducting layer

The anomalous Hall voltage of magnetic heterostructures plays a key role as the indicator for the magnetization state and its interplay with a variety of spintronic effects. In this letter, we report the observation, mechanism, and impact of the universal, dramatic scaling of the anomalous Hall voltage of magnetic heterostructures with the thickness and resistivity of the nonmagnetic conducting layers (e.g., normal metal) by combining transport experiments, analytical derivation, and finite-element analyses. We identify that the mechanism is the serial resistor effect of the magnetic and non-magnetic layers within the magnetic heterostructures and irrelevant to any Fermi surface variation or angular momentum injection from the nonmagnetic layer to the magnetic layer. We also show that the accuracy of the harmonic Hall voltage analyses of magnetic heterostructures are unaffected by the under-measuring of the anomalous Hall voltage and other transverse voltages due to the serial resistor effect. These findings provide crucial information for understanding a variety of spintronic phenomena involving the anomalous Hall and other transverse voltages.

cond-mat.mes-hall↗

arXiv2026

Negligible current-induced torque from the bulk and interface of Al

The light metal Al was predicted to have strong orbital Hall and Rashba effects from its bulk and interface, respectively. In this letter, we report experimental evidence that neither the bulk nor the interface of the Al contributed a detectable torque on adjacent Co and FePt layers with significant spin Hall effect, spin-orbit coupling, and resistivity mismatch with Al. These results suggest minimal orbital-spin conversion in Al and negligible orbital transport and spin-vorticity torque in Co/Al, Al/Co, and Al/FePt bilayers. Our findings suggest poor generality and/or effectiveness of torque contributions by the orbital Hall effect, the interfacial orbital Rashba effect, and the spin-vorticity coupling.

cond-mat.mes-hall↗

arXiv2026

AsyncMDE: Real-Time Monocular Depth Estimation via Asynchronous Spatial Memory

Foundation-model-based monocular depth estimation offers a viable alternative to active sensors for robot perception, yet its computational cost often prohibits deployment on edge platforms. Existing methods perform independent per-frame inference, wasting the substantial computational redundancy between adjacent viewpoints in continuous robot operation. This paper presents AsyncMDE, an asynchronous depth perception system consisting of a frozen foundation model and a lightweight fast path that amortizes the foundation model's computational cost over time. The foundation model periodically produces high-quality spatial features in the background, while the lightweight fast path runs asynchronously in the foreground, fusing cached memory with current observations through complementary fusion, outputting depth estimates, and autoregressively updating memory. This enables cross-frame feature reuse with bounded accuracy degradation. With 3.83M trainable fast-path parameters and a 97.5M frozen slow path, AsyncMDE's fast path operates at 237 FPS on an RTX 4090, recovering 77% of the accuracy gap to the foundation model. Across indoor static, dynamic, and synthetic extreme-motion benchmarks, AsyncMDE degrades predictably and reaches 161 FPS fast-path inference on a TensorRT-optimized Jetson AGX Orin, supporting real-time edge deployment.

cs.RO↗

arXiv2026

Absence of orbital current torque in a magnetic metal/Pt/CuOx trilayer

Naturally oxidized copper (CuOx) was cited as an exceptionally strong orbital-current source despite the keen debate over the concept of orbital current. Here, we report unambiguous experimental evidence for the absence of a detectable orbital-current torque in the Fe/Pt/CuOx trilayers. Using a magnetic metal detector of Fe thin film with a negligible self-induced torque, the damping-like torque due to Pt/CuOx bilayers is clarified to entirely arise from the spin Hall spin current of the Pt. As the Pt thickness increases, the torque for Fe/Pt/CuOx and Fe/Pt/MgO increases coherently and monotonically, as exactly expected from the spin Hall effect of Pt and the drift-diffusion model of spin angular momentum. These findings suggest poor generality or even universal absence of orbital current torque.

cond-mat.mtrl-sci↗

arXiv2026

PEPA: a Persistently Autonomous Embodied Agent with Personalities

Living organisms exhibit persistent autonomy through internally generated goals and self-sustaining behavioral organization, yet current embodied agents remain driven by externally scripted objectives. This dependence on predefined task specifications limits their capacity for long-term deployment in dynamic, unstructured environments where continuous human intervention is impractical. We propose that personality traits provide an intrinsic organizational principle for achieving persistent autonomy. Analogous to genotypic biases shaping biological behavioral tendencies, personalities enable agents to autonomously generate goals and sustain behavioral evolution without external supervision. To realize this, we develop PEPA, a three-layer cognitive architecture that operates through three interacting systems: Sys3 autonomously synthesizes personality-aligned goals and refines them via episodic memory and daily self-reflection; Sys2 performs deliberative reasoning to translate goals into executable action plans; Sys1 grounds the agent in sensorimotor interaction, executing actions and recording experiences. We validate the framework through real-world deployment on a quadruped robot in a multi-floor office building. Operating without reliance on fixed task specifications, the robot autonomously arbitrates between user requests and personality-driven motivations, navigating elevators and exploring environments accordingly. Quantitative analysis across five distinct personality prototypes demonstrates stable, trait-aligned behaviors. The results confirm that personality-driven cognitive architectures enable sustained autonomous operation characteristic of persistent embodied systems. Code and demo videos are available at https://sites.google.com/view/pepa-persistent/.

cs.RO↗

arXiv2026

A Common Lyapunov Matrix Approach to the Exponential Stability of Augmented Primal-Dual Gradient Flow as LPV Systems

We show that a common Lyapunov matrix exists for the convex combination of two Hurwitz matrices if and only if the intersection of the set of strict Lyapunov matrices for one matrix and the set of non-strict Lyapunov matrices for the other is nonempty. This simple relaxation is useful for the convergence analysis of the augmented primal-dual gradient flow for constrained optimization problems with affine inequality constraints, which can be viewed as a polytopic linear parameter-varying (LPV) system driven by the active-constraint selector. Under a relaxed strong convexity condition, exponential convergence is proved for the LPV system. The analysis can further be extended to the integral quadratic constraints (IQCs) framework for LPV systems to facilitate numerical search of the convergence rate.

eess.SY↗

arXiv2026

MoRI: Mixture of RL and IL Experts for Long-Horizon Manipulation Tasks

Reinforcement Learning (RL) and Imitation Learning (IL) are the standard frameworks for policy acquisition in manipulation. While IL offers efficient policy derivation, it suffers from compounding errors and distribution shift. Conversely, RL facilitates autonomous exploration but is frequently hindered by low sample efficiency and the high cost of trial and error. Since existing hybrid methods often struggle with complex tasks, we introduce Mixture of RL and IL Experts (MoRI). This system dynamically switches between IL and RL experts based on the variance of expert actions to handle coarse movements and fine-grained manipulations. MoRI employs an offline pre-training stage followed by online fine-tuning to accelerate convergence. To maintain exploration safety and minimize human intervention, the system applies IL-based regularization to the RL component. Evaluation across four complex real-world tasks shows that MoRI achieves an average success rate of 97.5% within 2 to 5 hours of fine-tuning. Compared to baseline RL algorithms, MoRI reduces human intervention by 85.8% and shortens convergence time by 21%, demonstrating its capability in robotic manipulation.

cs.RO↗

arXiv2026

Achieving distributed convex optimization within prescribed time for high-order nonlinear multiagent systems

In this paper, we address the distributed prescribed-time convex optimization (DPTCO) problem for a class of nonlinear multi-agent systems (MASs) under undirected connected graph. A cascade design framework is proposed such that the DPTCO implementation is divided into two parts: distributed optimal trajectory generator design and local reference trajectory tracking controller design. The DPTCO problem is then transformed into the prescribed-time stabilization problem of a cascaded system. Changing Lyapunov function method and time-varying state transformation method together with the sufficient conditions are proposed to prove the prescribed-time stabilization of the cascaded system as well as the uniform boundedness of internal signals in the closed-loop systems. The proposed framework is then utilized to solve robust DPTCO problem for a class of chain-integrator MASs with external disturbances by constructing a novel variables and exploiting the property of time-varying gains. The proposed framework is further utilized to solve the adaptive DPTCO problem for a class of strict-feedback MASs with parameter uncertainty, in which backstepping method with prescribed-time dynamic filter is adopted. The descending power state transformation is introduced to compensate the growth of increasing rate induced by the derivative of time-varying gains in recursive steps and the high-order derivative of local reference trajectory is not required. Finally, theoretical results are verified by two numerical examples.

math.OC↗

arXiv2026

DepthCache: Depth-Guided Training-Free Visual Token Merging for Vision-Language-Action Model Inference

Vision-Language-Action (VLA) models enable generalist robotic manipulation but suffer from high inference latency. This bottleneck stems from the massive number of visual tokens processed by large language backbones. Existing methods either prune or merge tokens uniformly, degrading the spatial reasoning essential for robotic control. We present DepthCache, a training-free framework that leverages depth as a structural prior for visual token compression. It partitions observations into depth-based regions and applies spatially differentiated merge ratios, preserving the near-field workspace while compressing the distant background. To exploit temporal redundancy, DepthCache distributes the merging process across consecutive frames, ensuring consistent representations while reducing per-step computation. A motion-adaptive pipeline further optimizes auxiliary view compression based on end-effector dynamics. The framework requires no model modification, generalizing across diverse VLA architectures. On the LIBERO benchmark, DepthCache achieves up to 1.28x inference speedup with less than 1% average success rate degradation across three VLA models (pi_0.5, OpenVLA, GR00T), whereas pruning and merging baselines incur 4--24% degradation at comparable compression. Real-world experiments on a physical manipulator demonstrate that DepthCache enables faster task throughput and more responsive closed-loop control in latency-sensitive scenarios.

cs.RO↗

arXiv2026

Omnidirectional Humanoid Locomotion on Stairs via Unsafe Stepping Penalty and Sparse LiDAR Elevation Mapping

Humanoid robots, characterized by numerous degrees of freedom and a high center of gravity, are inherently unstable. Safe omnidirectional locomotion on stairs requires both omnidirectional terrain perception and reliable foothold selection. Existing methods often rely on forward-facing depth cameras, which create blind zones that restrict omnidirectional mobility. Furthermore, sparse post-contact unsafe stepping penalties lead to low learning efficiency and suboptimal strategies. To realize safe stair-traversal gaits, this paper introduces a single-stage training framework incorporating a dense unsafe stepping penalty that provides continuous feedback as the foot approaches a hazardous placement. To obtain stable and reliable elevation maps, we build a rolling point-cloud mapping system with spatiotemporal confidence decay and a self-protection zone mechanism, producing temporally consistent local maps. These maps are further refined by an Edge-Guided Asymmetric U-Net (EGAU), which mitigates reconstruction distortion caused by sparse LiDAR returns on stair risers. Simulation and real-robot experiments show that the proposed method achieves a near-100\% safe stepping rate on stair terrains in simulation, while maintaining a remarkably high safe stepping rate in real-world deployments. Furthermore, it completes a continuous long-distance walking test on complex outdoor terrains, demonstrating reliable sim-to-real transfer and long-term stability.

cs.RO↗

arXiv2026

A Gait Driven Reinforcement Learning Framework for Humanoid Robots

This paper presents a real-time gait driven training framework for humanoid robots. First, we introduce a novel gait planner that incorporates dynamics to design the desired joint trajectory. In the gait design process, the 3D robot model is decoupled into two 2D models, which are then approximated as hybrid inverted pendulums (H-LIP) for trajectory planning. The gait planner operates in parallel in real time within the robot's learning environment. Second, based on this gait planner, we design three effective reward functions within a reinforcement learning framework, forming a reward composition to achieve periodic bipedal gait. This reward composition reduces the robot's learning time and enhances locomotion performance. Finally, a gait design example, along with simulation and experimental comparisons, is presented to demonstrate the effectiveness of the proposed method.

cs.RO↗

arXiv2026

A Three-Level Whole-Body Disturbance Rejection Control Framework for Dynamic Motions in Legged Robots

This paper presents a control framework designed to enhance the stability and robustness of legged robots in the presence of uncertainties, including model uncertainties, external disturbances, and faults. The framework enables the full-state feedback estimator to estimate and compensate for uncertainties in the whole-body dynamics of the legged robots. First, we propose a novel moving horizon extended state observer (MH-ESO) to estimate uncertainties and mitigate noise in legged systems, which can be integrated into the framework for disturbance compensation. Second, we introduce a three-level whole-body disturbance rejection control framework (T-WB-DRC). Unlike the previous two-level approach, this three-level framework considers both the plan based on whole-body dynamics without uncertainties and the plan based on dynamics with uncertainties, significantly improving payload transportation, external disturbance rejection, and fault tolerance. Third, simulations of both humanoid and quadruped robots in the Gazebo simulator demonstrate the effectiveness and versatility of T-WB-DRC. Finally, extensive experimental trials on a quadruped robot validate the robustness and stability of the system when using T-WB-DRC under various disturbance conditions.

cs.RO↗

arXiv2026

Evidence for strong localization of orbital polarization

Whether orbital polarization propagates has become the most essential question of the blooming orbitronics that aims to generate non-local orbital torque and orbital pumping. Recent theories have suggested a strong orbital Hall effect within the light metal Al and a strong orbital Rashba effect at Co/Al interfaces, providing ideal platforms for experimental verification of possible orbital transport effects. Here, we report robust experimental evidence for the strong localization of orbital polarization. We demonstrate that neither the bulk nor the interface of the Al contributes a detectable orbital torque on adjacent magnetic layer with strong bulk and interfacial spin-orbit coupling necessary for potential orbital-spin conversion. These results have clarified that orbital polarization undergoes much faster relaxation than spin polarization and hardly participates in non-local accumulation, transport, or torque generation. The experimental evidence for strong localization of orbital polarization represents a groundbreaking advance towards solving the essential orbital torque debate.

cond-mat.mes-hall↗

arXiv2025

Hybrid Dynamics Modeling and Trajectory Planning for a Cable-Trailer System with a Quadruped Robot

Inspired by sled-pulling dogs in transportation, we present a cable-trailer integrated with a quadruped robot system. The motion planning of this system faces challenges due to the interactions between the cable's state transitions, the trailer's nonholonomic constraints, and the system's underactuation. To address these challenges, we first develop a hybrid dynamics model that captures the cable's taut and slack states. A search algorithm is then introduced to compute a suboptimal trajectory while incorporating mode transitions. Additionally, we propose a novel collision avoidance constraint based on geometric polygons to formulate the trajectory optimization problem for the hybrid system. The proposed method is implemented on a Unitree A1 quadruped robot with a customized cable-trailer and validated through experiments. The real system demonstrates both agile and safe motion with cable mode transitions.

cs.RO↗