This paper introduces AirLock+, an end-to-end vision system for scalable UAV-to-satellite image registration, enabling two key downstream tasks: (i) precise target geolocalization in geodetic coordinates and (ii) geospatial augmented reality to elevate situation awareness. AirLock+ comprises three modules: A predictive tracker first localizes targets in UAV image frames, while a cross-view image matcher generates robust UAV-to-satellite homographies that withstand severe domain gaps, outdated satellite imagery, and generalize to unseen environments without finetuning. The resulting pixel-to-world correspondences enable target pixel coordinates to be mapped into geodetic space, yielding continuous trajectory estimates and supporting geospatial augmentation of UAV video feeds. Our system achieves an average target localization error of 20.23 m across 7.8 km real-world trajectories, demonstrating robustness in high-altitude, oblique-view conditions where existing methods typically fail.

Manipulating thin objects requires precise contact geometry and reliable force perception, yet many anthropomorphic robotic hands lack the mechanical and sensing capabilities needed for such interactions. We present the ARISTO Hand, a tendon-driven robotic hand that integrates active distal hyperextension with a hybrid fingertip-sensing architecture that combines a rigid, nail-mounted force-torque sensor and a soft capacitive tactile array. Active hyperextension enables controlled fingertip engagement beyond the kinematic limits of standard flexion, increasing pull-out force by 2.76x for object thicknesses of 1-20 mm while preserving the nominal grasp capability. The rigid nail-mounted sensor provides reliable force measurements during edge contacts, where the sensitivity of proprioceptive force estimation degrades as the contact geometry approaches kinematic singularities. We validate the proposed architecture through quantitative force characterization and a multi-stage SD card extraction and insertion task. Video and supplementary materials are available at: https://aristohand.github.io

Compliant underactuated mechanisms are well-suited to safe physical human–robot interaction, but their use in robotic physical therapy is limited by modeling assumptions that poorly capture human limb geometry and by payload capacities insufficient to support human limbs. This work presents a higher-fidelity quasi-static force-transmission model, a design optimization framework, and a novel embodiment of a compliant five-bar linkage gripper. The model relaxes three assumptions common in prior work-zero-thickness finger pads, circular object cross-sections, and fixed midpoint contact-by computing contact locations online for elliptical limb geometries and accounting for palm reaction forces. A discrete-gradient optimization framework simultaneously synthesizes linkage dimensions and compliance to balance mechanical advantage against feasible workspace coverage. These contributions are validated through the ANTERO gripper, a 1.54 kg admittance-controlled end-effector. Without tactile sensors, it estimates multi-contact grasp forces within 15% of measured values, conservatively overestimating applied loads. The closed-loop bandwidth is 1.28 - 2.74 Hz, and the payload capacity of approximately 160 N exceeds that of comparable commercial adaptive grippers

Deploying embodied AI agents in the physical world demands cognitive capabilities for long-horizon planning that execute reliably, deterministically, and transparently. We present HARMONIC, a cognitive-robotic architecture that pairs OntoAgent, a content-centric cognitive architecture providing metacognitive self-monitoring, domain-grounded diagnosis, and consequence-based action selection over ontologically structured knowledge, with a modular reactive tactical layer. HARMONIC's modular design enables a functional evaluation of whether LLMs can replicate OntoAgent's cognitive capabilities, evaluated within the same robotic system under identical conditions. Six LLMs spanning frontier and efficient tiers replace OntoAgent in a collaborative maintenance scenario under native and knowledge-equalized conditions. Results reveal that LLMs do not consistently assess their own knowledge state before acting, causing downstream failures in diagnostic reasoning and action selection. These deficits persist even with equivalent procedural knowledge, indicating the issues are architectural rather than knowledge-based. These findings support the design of physically embodied systems in which cognitive architectures retain primary authority for reasoning, owing to their deterministic and transparent characteristics.

Multi-suction-cup grippers are often used to perform pick-and-place robotic tasks, especially in industrial settings where grasping a wide range of light to heavy objects in limited amounts of time is a common requirement. However, most existing works focus on using one or two suction cups to grasp only lightweight objects with irregular shapes. There is a lack of research on robust manipulation of heavy objects using larger arrays of suction cups, which introduces challenges in modeling and predicting grasp failure. This paper presents a general approach to modeling grasp strength in multi-suction-cup grippers, introducing new constraints usable for trajectory planning and optimization to achieve fast and reliable pick-and-place maneuvers. The primary modeling challenge is the accurate prediction of the distribution of loads at each suction cup while grasping objects. To solve for this load distribution, we find minimum spring potential energy configurations through a simple quadratic program. This results in a computationally efficient analytical solution that can be integrated to formulate grasp failure constraints in time-optimal trajectory planning. Finally, we present experimental results to validate the efficiency and accuracy of the proposed model.

We present the PLATO Hand, a dexterous robotic hand with a hybrid fingertip that combines a rigid fingernail, embedded distal phalanx, and compliant pulp to shape contact behavior during manipulation. By mechanically organizing how contact is initiated, supported, and transmitted at the fingertip, this structure creates stable and task-relevant contact conditions across diverse object geometries and grasp orientations. We develop a strain-energy-based bending-indentation model to guide the fingertip design and to explain how material stiffness and contact geometry govern deformation partitioning within the fingertip. Experiments show improved pinch stability, improved fingernail-mediated dorsal-contact force transmission and proprioceptive observability, and successful execution of edge-sensitive manipulation tasks, including paper singulation, card picking, and orange peeling. These results show that coupling a mechanically structured contact interface with a force-motion-transparent finger mechanism provides a principled approach to precise manipulation.

Despite the rise of mobile robot deployments in community settings, the perceived safety of cohabitants remains understudied in many domains. To address this gap, we perform a study to identify elements of indoor human–mobile robot encounters that impact perceived safety. This study evaluates the effects of robot movement behavior and the number of robots nearby on perceived safety of participants. Further, this article investigates how the presence of other people impacts perceived safety in such settings. We leverage methodologies from physiological signal analysis, autonomy, surveys, and qualitative interviews to decode insights into the human experience during such encounters. Particularly, signal analysis yielded that the presence of multiple robots decreases perceived safety and that search behaviors were more comfortable than navigation behaviors. Similarly, interviews with participants demonstrated clear effects on perceived safety in the presence of others, and that sensemaking was a key component involved in their perceptions of safety. When the data were combined, interview data revealed that near collisions between the robots likely confounded the signal analysis findings with respect to the number of robots and their movement behavior. The data types agree that the presence of a robot impacts perceived safety; however, there are also conflicting results that we discuss, which highlight that near-collisions impact perceived safety. In aggregate, the study illustrates the benefits of leveraging eclectic methods to ascertain deeper insights. Overall, the article aims to unlock insights into human perceptions during encounters with community embedded robots, which can be used in the future design of such systems.

Dynamic surface electromyography (sEMG)-based muscle fatigue assessment is often compromised by sensor instability, motion artifacts, and signal nonstationarity during dynamic exercise. Here, we integrate a noninvasive, skin-conformal e-tattoo sensor with a bandpass-Hampel-iterative ensemble empirical mode decomposition (BH-IEEMD) processing pipeline to suppress impulsive noise and stabilize fatigue-related features. Twenty participants wore the e-tattoo continuously for five days while performing daily dynamic exercises, with sEMG signals benchmarked against conventional gel electrodes. The e-tattoo maintained stable contact impedance, a noise floor comparable to gel electrodes, and higher signal-to-noise and signal-to-motion ratios during movement, without inducing skin irritation. BH-IEEMD significantly attenuated sub-20-Hz motion-induced power and transient artifacts, leading to improved window-level autocovariance stationarity. Relative to bandpass-only baselines, features extracted using BH-IEEMD exhibited tighter distributions, improved Normal-versus-Fatigue separability, and greater reproducibility of fatigue trends across days and subjects. Leave-one-subject-out evaluation confirmed model-agnostic performance gains, with the best-performing model achieving an average R2 = 0.70 (RMSE = 0.157) and best-subject performance reaching R2 = 0.93 (RMSE = 0.074). Together, long-term skin-conformable sensing and artifact-aware signal processing establish a robust framework for reliable multi-day muscle fatigue monitoring, enabling practical deployment in real-world rehabilitation, training, and wearable exoskeleton control.

Robots operating alongside humans must recognize what they do not know before acting, diagnose problems from domain knowledge, and reason about action consequences. These capabilities are operational requirements, not optimization targets, and their absence produces silent and unrecoverable failures. We present a first-of-its-kind controlled comparison between OntoAgent, our content-centric cognitive architecture, and six LLMs spanning frontier and efficient tiers as drop-in replacements at the strategic layer of the same robotic system in HARMONIC. LLMs fail to verify their knowledge state before acting, even when given equivalent procedural knowledge. The deficit is architectural, not knowledge-based. Knowledge-grounded architectures must retain decision authority; LLMs contribute where their strengths apply.

While sim2real efforts are necessary for effective policy transfer to hardware, there is such a thing as too much of a good thing. We argue that sim2real efforts have led to misaligned incentives with policy learning, resulting in simulator lock in and poor policy exploration due to the unreasonable constraints imposed by the real world. We offer a diagnosis and explanation of the current status of the problem, and propose a potential solution via a sim2sim2real paradigm that leverages the robot's kinematics as the sole design constraint.

Dexterous teleoperation requires precise arm-hand coordination, low-latency feedback, and robust interaction in real-world contact-rich environments. This paper presents a modular bilateral teleoperation framework that integrates operator-side input interfaces with a robot-side dexterous hand and compliant robotic arm in a unified control architecture. The system supports position-based hand retargeting, differential arm control, multi-scale haptic feedback, and shared control for stable manipulation. We validate the framework through a real-world dexterous manipulation task, highlighting coordinated arm-hand control and contact-aware interaction. Beyond feasibility, we identify key design insights related to cross-embodiment mismatch, haptic feedback granularity, and shared control. The proposed platform provides a practical teleoperation system and a foundation for collecting high-quality demonstrations for future learning-from-demonstration research.

We present AeroMap3D, a monocular 6-DoF UAV localization system that anchors onboard imagery to visual, geometric, and semantic map priors for GNSS-denied navigation. AeroMap3D addresses two fundamental challenges in map-referenced aerial localization: the cross-view discrepancy between UAV imagery and satellite maps, and the structural inconsistency between bare-earth digital elevation models (DEMs) and urban scenes. First, we introduce a lightweight adapter that enables a dense matcher pretrained on internet-scale generic data to perform reliable UAV-to-map registration without finetuning. By estimating the scale ratio and yaw offset between the UAV image and map tile, the adapter removes the dominant geometric misalignment induced by altitude, camera field of view, and heading before dense correspondence estimation. Second, AeroMap3D lifts 2D UAV-map correspondences onto DEM terrain while using OpenStreetMap annotations to reject semantically unreliable matches before RANSAC-PnP pose estimation, thereby reducing errors caused by unmodeled building heights and off-nadir structures. Delayed map-based pose measurements are further fused with relative-motion priors using a delayed-state EKF for continuous trajectory estimation. Without UAV-Terra3D retraining or tuning, AeroMap3D localizes all trajectories across eight Austin sites within 50 m and achieves 5.88 m mean 3D error over 55 km of flight.

Humanoid locomotion in highly confined environments requires navigating dense environmental obstacles and complex self-collision bounds while maintaining multi-contact dynamic feasibility. Traditional trajectory optimizers frequently struggle in these restricted spaces, as navigating the large collision space with splines on particle abstractions is insufficient and leads to poor local minima. To address this, we propose a three-stage whole-body planning framework that formulates kinematic path planning directly over kinematically reachable rigid-body volumes. By integrating differentiable collision avoidance into a reachability-constrained formulation, our framework synthesizes volume-informed guides that reliably guide a full-order trajectory optimizer over long horizons. We show that these optimized plans serve as high-quality references to train a residual reinforcement learning policy for robust online execution. We validate our approach on the Unitree G1 humanoid across three benchmark testbeds exceeding NIST emergency response standards, achieving restricted confinement ratios (C_r < 1.5). Our framework generates feasible trajectories across 12-to-18-second tasks with complex foot and hand contacts where standard baselines fail, while the learned policy successfully tracks these plans under extensive domain randomization in physics simulation.

Launched in October 2023, the Psyche spacecraft is en route to the asteroid (16) Psyche to study its exposed nickeliron core, relying primarily on its cold gas thrusters and reaction wheel assemblies for attitude control. The Guidance, Navigation, and Control (GN&C) team at the Jet Propulsion Laboratory (JPL) previously reported the linear stability values for these systems, showing the cold gas system (CGS) controller with a gain margin of 13.31 dB and phase margin of 74.4°, and the reaction wheel (RWA) controller with a gain margin of 13 dB and phase margin of 35.2°. However, these margins had not been verified against the spacecraft's nonlinear time-domain dynamics. This work addresses the verification gap by using Psyche's Controls Analysis System Testbed/GNC Integrated Systems Testbed (CAST/GIST) tool to conduct nonlinear simulations. Our results show that the gain margins for the CGS controller of the nonlinear system are within 0.3 dB of the linear values, while those for the RWA controller are within 1 dB. In both cases, the nonlinear results show wider margins than those predicted by the linear analysis, confirming the robustness of the spacecraft's attitude control system. These results provide the first validation of Psyche's stability margins in the nonlinear domain.

This paper addresses the problem of hierarchical task control, where a robotic system must perform multiple subtasks with varying levels of priority. A commonly used approach for hierarchical control is the null-space projection technique, which ensures that higher-priority tasks are executed without interference from lower-priority ones. While effective, the state-of-the-art implementations of this method rely on low-level controllers, such as PID controllers, which can be prone to suboptimal solutions in complex tasks. This paper presents a novel framework for hierarchical task control, integrating the null-space projection technique with the path integral control method. Our approach leverages Monte Carlo simulations for real-time computation of optimal control inputs, allowing for the seamless integration of simpler PID-like controllers with a more sophisticated optimal control technique. Through simulation studies, we demonstrate the effectiveness of this combined approach, showing how it overcomes the limitations of traditional methods by optimizing the task performance.

This paper studies the synthesis and mitigation of stealthy attacks in nonlinear cyber-physical systems (CPS). To quantify stealthiness, we employ the Kullback-Leibler (KL) divergence, a measure rooted in hypothesis testing and detection theory, which captures the trade-off between an attacker's desire to remain stealthy and her goal of degrading system performance. First, we synthesize the worst-case stealthy attack in nonlinear CPS using the path integral approach. Second, we consider how a controller can mitigate the impact of such stealthy attacks by formulating a minimax KL control problem, yielding a zero-sum game between the attacker and the controller. Again, we leverage a path integral-based solution that computes saddle-point policies for both players through Monte Carlo simulations. We validate our approach using unicycle navigation and cruise control problems, demonstrating how an attacker can covertly drive the system into unsafe regions, and how the controller can adapt her policy to combat the worst-case attacks.

This paper presents an open-source, lightweight, yet comprehensive software framework, named RPC, which integrates physics-based simulators, planning and control libraries, debugging tools, and a user-friendly operator interface. RPC enables users to thoroughly evaluate and develop control algorithms for robotic systems. While existing software frameworks provide some of these capabilities, integrating them into a cohesive system can be challenging and cumbersome. To overcome this challenge, we have modularized each component in RPC to ensure easy and seamless integration or replacement with new modules. Additionally, our framework currently supports a variety of model-based planning and control algorithms for robotic manipulators and legged robots, alongside essential debugging tools, making it easier for users to design and execute complex robotics tasks. The code and usage instructions of RPC are available at https://github.com/shbang91/rpc.

This paper explores the problem of planning for visual search without prior map information. We leverage the pixel-wise environment perception problem where one is given wide Field of View 2D scan data and must perform LiDAR segmentation to contextually label points in the surroundings. These pixel classifications provide an informed prior on which to plan next best viewpoints during visual search tasks. We present LIVES: LiDAR Informed Visual Search, a method aimed at finding objects of interest in unknown indoor environments. A robust map-free classifier is trained from expert data collected using a simple cart platform equipped with a map-based classifier. An autonomous exploration planner takes the contextual data from scans and uses that prior to plan viewpoints more likely to yield detection of the search target. We propose a utility function that accounts for traditional metrics like information gain and path cost and for the contextual information. LIVES is baselined against several existing exploration methods in simulation to verify its performance. It is validated in real-world experiments with single and multiple search objects with a Spot robot in two unseen environments. Videos of experiments, implementation details and open source code can be found at https://sites.google.com/view/lives-2024/home.