Searcharxiv⌕ Search

arXiv subjects

Ravi Prakash

Publications and source records attributed to Ravi Prakash.

At least 19 recordsLinked to original sources

An Open-Source da Vinci X/Xi Instrument Module for Laparoscopic Surgery Research

Studying electrosurgical tasks on a research robot requires control of both instrument motion and energy activation, along with a record of when each action occurs. This paper presents an open-source module for da Vinci X/Xi instruments on a UR5/UR5e robotic arm. Five motors transmit torque through timing belts to spring-loaded drive discs. An electrosurgical interposer accepts software commands, gives the surgeon's foot pedals priority, and records the source of each activation request. In bench testing, the interposer recorded all 12 activation and deactivation events from six pedal presses. Ex vivo demonstrations included monopolar and bipolar coagulation of splenic tissue and monopolar cutting during gallbladder dissection. Optical tracking of the Fenestrated Bipolar Forceps showed that calibration brought pitch and yaw gains from 0.904 and 1.14 to 1.00 and 1.02, respectively. The module enables researchers to record instrument motion, video, and the timing and source of electrosurgical commands during laparoscopic tasks.

cs.RO↗

EpiFlow: Bridging Safety and Performance in Offline Reinforcement Learning via Epigraph-Guided Flow Matching

Offline reinforcement learning (RL) offers a promising framework for deploying autonomous systems in safety-critical settings without the risks of online exploration. However, learning policies that simultaneously achieve high performance and strong safety guarantees from fixed datasets remains a fundamental challenge. Many existing safe offline RL approaches typically rely on soft constraint formulations, which may permit safety violations and are sensitive to distributional shift. In contrast, formal methods such as Hamilton--Jacobi (HJ) reachability and Control Barrier Functions (CBFs) provide rigorous safety guarantees, but often yield overly conservative solutions, often neglecting performance. In this work, we bridge this gap by formulating safe offline RL as a state-constrained optimal control problem, where safety is enforced through hard state constraints and performance is captured via a reward function. The resulting value function satisfies a Hamilton--Jacobi--Bellman (HJB) equation, which we approximate using offline RL on fixed datasets by learning an epigraph feasibility value function and extracting policies via flow matching. This formulation enables principled integration of safety guarantees with data-driven policy optimization. Empirically, across safety-critical benchmarks including boat navigation, Safety-Gymnasium, and Bullet-Safety-Gym tasks, our approach achieves competitive returns while exhibiting near-zero constraint violations, demonstrating a favorable balance between safety and performance in the offline setting.

cs.LG↗

When does the head leave? Shared timing and a movement clock in 360-degree video viewing

A $360^\circ$ streaming system only needs high quality where the viewer faces, so knowing when a head will turn away matters as much as where it will go. Across four public head-tracking datasets, two used to fix and validate the method and two held out for testing, three patterns emerge on the held-out sets. First, viewers facing the same region turn away within a second of one another far more often than time-shifted traces allow. That estimate is about five times the pairwise threshold for a video timing one departure in ten, mapping to roughly one and a third to over twice that one-in-ten share. The excess co-departing fraction is 0.0422, with a 90% interval from 0.0279 to 0.0565. Second, time since the last large head movement improves held-out departure prediction beyond video and viewer effects. It adds 0.0793 nats per departure, a predictive dependence rather than proof of an internal timer. Third, on the eye-tracked test set, gaze crosses the region boundary after the head starts moving, lagging head onset by 0.30 s. Because headsets record continuous angles, a departure exists only after a rule marks when a settled hold ends once the head swings past a speed and angle threshold. Before touching the test sets, we picked one primary setting for the headline estimates above and tested 18 settings on synthetic traces with planted answers, requiring at least nine passing settings for robustness. Fifteen settings passed for the clock and all 15 valid settings confirm its gain; 8 passed for synchrony and all 8 valid settings agree, one short of the nine-setting bar; and 6 of 7 dual-validated settings agree on gaze lag. Synchrony validation drops from 17 or 18 passing settings under guessed noise to 8 under measured noise because zero-tolerance rules reject a small baseline offset, consistently positive at one dataset size, as datasets grow.

cs.MM↗

Self-Learning Surprise Detection in Spatial Audio for Viewport-Aware 360-Video Streaming

Adaptive streaming of 360-degree video relies on viewport prediction to allocate bandwidth efficiently. Current approaches predominantly use visual saliency or historical gaze patterns, neglecting the role of spatial audio in guiding user attention. This paper presents a self-learning framework for detecting "surprising" auditory events, moments that deviate from learned temporal expectations, and demonstrates their utility for viewport prediction. The proposed architecture combines SE(3)-equivariant graph neural networks with recurrent temporal modeling, trained via a dual self-supervised objective. A key feature is the natural modeling of temporal attention decay: surprise is high at event onset but diminishes as the listener adapts. Experiments on the AVTrack360 dataset show that integrating audio surprise with visual cues reduces bitrate waste by up to 18% compared to visual-only methods.

cs.MM↗

Embodiment-Aware Planning for Heterogeneous Bimanual Manipulation

Many manipulation tasks that are effortless for dexterous human hands remain challenging for robotic systems equipped with simple, task-specialized grippers. Industrial platforms commonly rely on end-effectors such as suction cups or parallel-jaw grippers, yet no single mode can reliably satisfy the diverse constraints encountered across different phases of complex manipulation tasks, including pickup, reorientation, insertion, and constrained placement. In this work, we investigate whether complementary simple grippers within a heterogeneous bimanual setup can collectively realize tasks that exceed the capability of any individual gripper alone. Given a single human demonstration specifying the desired object motion, we formulate embodiment-aware execution as a finite-horizon optimization over arm-trajectory assignments. At each segment, the planner determines whether single-arm manipulation or a coordinated dual arm handover is required, jointly reasoning over heterogeneous grasp feasibility, motion constraints, manipulability, and cross-gripper compatibility. Exploiting this formulation, we compute globally consistent assignments with explicit switching regularization. Experiments on a dual Franka FR3 platform equipped with suction and parallel-jaw grippers demonstrate improved feasibility and reliability in tasks that are infeasible under single-gripper execution.

cs.RO↗

Asymmetric quantum information scrambling in inhomogeneous XXZ spin chains

Inhomogeneous systems have become increasingly relevant in experimentally engineered quantum many-body systems, where spatially varying interaction strengths can significantly influence nonequilibrium dynamics. Motivated by this, we numerically study the out-of-time-ordered correlators (OTOCs) in inhomogeneous XXZ spin chains. Using two types of spatially varying interaction profiles, namely, linear-gradient and stepwise profiles, we show that spatial inhomogeneity in the interactions can induce pronounced asymmetry in information scrambling, with OTOC operators located at different sites exhibiting distinct dynamical behavior. In particular, OTOCs associated with the strongly interacting side exhibit suppressed scrambling compared to those associated with the weakly interacting side, with the difference becoming more pronounced when the interaction strengths differ significantly. To elucidate the origin of the long-time saturation of OTOCs, we analyze the diagonal matrix elements of the OTOC observables in the energy eigenbasis and their overlap with the Hamiltonian, which explicitly incorporates the spatial interaction profile. The resulting analytical expression is consistent with the numerical results. Finally, we extend our analysis to periodically driven inhomogeneous spin chains and show that the interaction-gradient-induced asymmetry persists under periodic driving.

quant-ph↗

OCTN: Neural OCT Representations for Robot-Guided Precision Intervention

Optical coherence tomography (OCT) offers compact, contactless, micron-scale imaging suitable for intraoperative guidance, but native OCT volumes are discretely sampled, anisotropic, and currently inefficient for downstream geometric reasoning and robot integration. We present OCTN (pronounced "octane"), an implicit neural representation framework that converts volumetric OCT scans into a continuous, differentiable, and spatially faithful tissue-intensity field. OCTN uses a two-stage hybrid training strategy that combines supervision from acquired voxels with inter-slice interpolations, preserving B-scan fidelity while improving continuity in sparsely sampled regions. For versatility, we first show that OCTN enables fast volumetric reasoning by storing the learned tissue representation natively on the GPU, supporting intensity-based spatial queries with up to 43x speedup over conventional CPU processing. We then demonstrate OCTN-enabled OCT-guided robotic laser surgery where the continuous tissue representation supports implicit surface discovery and surface-constrained path planning via multiple optimization strategies, including Newton- and SGD-based optimization. Next, OCTN enables reconstruction of dense volumetric structure from sparsely acquired B-scans, while reducing acquisition time by 4x and preserving clinically relevant structures. Across the newly generated Duke TissueOCT dataset and public OCT datasets, OCTN achieves robust, high-fidelity reconstruction with PSNR > 30 dB and training time < 10 s, while preserving surface consistency within 10 $μ$m Chamfer distance relative to baseline reconstruction. The TissueOCT dataset and code are publicly available at raprakashvi.github.io/octn

cs.RO↗

Gripper-aware Vision Language Action Models

Vision language action models (VLAs) have advanced general purpose robotic grasping and manipulation by enabling robots to interpret visual observations and natural language instructions to generate executable action sequences. However, existing VLAs often implicitly assume gripper invariance, despite grasping strategies being inherently embodiment-dependent. Different gripper types, such as parallel-jaw and suction, usually require distinct interaction strategies to achieve the same grasping objective. Moreover, current datasets for VLAs predominantly rely on parallel-jaw grippers, limiting gripper-aware learning. To address this gap, we introduce MiGA, a multi-gripper-aware dataset spanning five distinct gripper types across multiple robots with 103,000 demonstrations, explicitly capturing strategy divergence under shared task objectives. We further propose GVLA, which combines a new multi-gripper tokenizer with adapter-based policy routing. Our new gripper encoding induces structured embedding information that balances parameter sharing and strategy differentiation, while layer-wise probing confirms meaningful gripper-conditioned representations for VLAs. Intensive experiments in both simulation and real-world robots show that our GVLA outperforms the current baselines across evaluated settings. Our method also improves zero-shot generalization or few-shot adaptation to new objects or unseen tasks, and enable more efficient gripper adaptation.

cs.RO↗

Design and Evaluation of a Compliant Quasi Direct Drive End-effector for Safe Robotic Ultrasound Imaging

Robot-assisted ultrasound scanning promises to advance autonomous and accessible medical imaging. However, ensuring patient safety and compliant human-robot interaction during probe contact poses a significant challenge. Most existing systems either have high mechanical stiffness or trade performance for compliance. This paper presents a novel compliant end-effector designed to mount on robotic arms for safe and accurate robotic ultrasound imaging, using a quasi-direct drive actuator to achieve passive mechanical compliance and precise active force control. To evaluate the end-effector's performance, we developed an ex vivo dynamic motion simulator platform for contact and scanning testing on tissue under simulated movements. The end-effector was evaluated against a UR3e robot arm using conventional force control strategies as a baseline. Single-point contact experiments from 2.5 N to 15 N show that the end-effector reduced force tracking RMS error by 80.1% on average. Trajectory scanning experiments at different speeds showed an average of 68.0% reduction in force tracking error. Statistically significant improvements were observed in four of six quantitative image quality and stability metrics using the end-effector. This work presents a novel approach for designing and evaluating compliant end-effectors, with the goal of improving safety and reliability in robotic ultrasound.

cs.RO↗

Embodied Passive Aeroacoustic Perception Enables Relative Sensing and Pursuit Between Aerial Robots

Aerial robots generate structured aeroacoustic fields during flight, yet these signals have been underexplored as a source of onboard relative perception, particularly under the strong ego-acoustic interference generated during simultaneous flight in various outdoor conditions. We introduce embodied passive aeroacoustic perception, a sensing paradigm in which an aerial robot infers actionable relative-state information from the naturally generated sound of flight while operating within its own evolving aeroacoustic field. We present SonicFly, a passive aeroacoustic perception framework that enables one unmanned aerial vehicle to estimate and follow another using only the leader's intrinsic flight sound, without active acoustic signaling, inter-robot communication, GPS sharing, or external sensing infrastructure. The system uses a lightweight four-microphone array, rotorcraft-informed acoustic representations, a neural bearing-range estimator, and confidence-gated filtering for closed-loop flight. Through acoustic characterization, onboard localization, and outdoor pursuit experiments, we show that multirotor aeroacoustic signals contain sufficient information to support relative perception despite strong ego-acoustic interference, environmental variability, and changing flight geometry. During acoustic-only pursuit, SonicFly achieved a mean distance-maintenance error of 1.34 m across diverse outdoor trajectories and operating conditions. Analysis of the acoustic channel reveals design principles governing embodied passive aeroacoustic perception, including the roles of harmonic structure, spectral separability, and spatial acoustic cues in determining observability. Our results establish the feasibility of embodied passive aeroacoustic perception for aerial robots and suggest that naturally generated behavioral signals can serve as information for robotic perception and coordination.

cs.RO↗

Beyond Visual Grasping: Benchmarking Complex Grasping from Detection to Execution

Robust robotic grasping remains a fundamental challenge for complex real-world applications. Recent advances in large-scale models demonstrate promising capabilities for reasoning in robotic tasks. However, existing benchmarks for grasping primarily focus on isolated, visual-based grasp pose detection, failing to capture the complexity of grasping tasks that require multi-step reasoning and semantic understanding during execution. To address this gap, we propose GCA-Bench, a benchmark featuring challenging \textit{grasping with complex action} scenarios that involve both scene-level reasoning and semantic constraints. GCA-Bench enables the evaluation of recent large foundation models under the same settings. To demonstrate the effectiveness of our new benchmark, we implement a diverse set of baselines, ranging from traditional grasp detection pipelines to end-to-end learning methods. Empirical studies achieve success rates below 70\% on complex grasping scenarios, underscoring critical limitations. In addition, we propose new evaluation metrics, analyze critical failure models, and provide insights to guide the development of more robust and generalizable grasping strategies.

cs.RO↗

Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies

Offline safe reinforcement learning (RL) seeks reward-maximizing policies from static datasets under strict safety constraints. Existing methods often rely on soft expected-cost objectives or iterative generative inference, which can be insufficient for safety-critical real-time control. We propose Safe Flow Q-Learning (SafeFQL), which extends FQL to safe offline RL by combining a Hamilton--Jacobi reachability-inspired safety value function with an efficient one-step flow policy. SafeFQL learns the safety value via a self-consistency Bellman recursion, trains a flow policy by behavioral cloning, and distills it into a one-step actor for reward-maximizing safe action selection without rejection sampling at deployment. Empirically, SafeFQL trades modestly higher offline training cost for substantially lower inference latency than diffusion-style safe generative baselines, which is advantageous for real-time safety-critical deployment. Across boat navigation, and Safety Gymnasium MuJoCo tasks, SafeFQL matches or exceeds prior offline safe RL performance while substantially reducing constraint violations.

cs.LG↗

Learning from Demonstration via Spatiotemporal Tubes for Unknown Euler-Lagrange Systems

We present STT-LfD, a unified Learning from Demonstration (LfD) framework that integrates motion learning with control for unknown Euler-Lagrange systems. Unlike traditional decoupled approaches that track a fixed reference, the proposed method treats demonstrations as a data-driven safety specification. Using heteroscedastic Gaussian Processes, STT-LfD learns Spatiotemporal Tubes (STTs) as an intent envelope that capture time-varying precision requirements of a task. A closed-form feedback controller then enforces these learned constraints while respecting actuator limits, without requiring explicit system identification. The approach preserves the temporal structure of demonstrations, remains computationally efficient, and avoids explicit system identification. Hardware experiments on a mobile robot and a 7-DOF manipulator show that it outperforms baselines in robustness to disturbances and computational speed.

cs.RO↗

HJ-SafeDMP: Hamilton-Jacobi Reachability-Guided Dynamic Movement Primitives for Provably Safe Robot Motion

Robots deployed in safety-critical environments must execute motions that are simultaneously robust to disturbances and provably safe from collisions. Dynamic Movement Primitives (DMPs) offer inherent stability, temporal flexibility, and efficient trajectory generalization from single demonstrations, but they lack formal safety certificates. Conversely, Hamilton-Jacobi (HJ) Reachability analysis provides a principled framework for computing worst-case safety margins and forward-invariant safe sets, but classical grid-based methods suffer from the curse of dimensionality and are impractical for real-time control. This paper introduces HJ-SafeDMP, a framework that integrates DMPs with learned HJ Reachability-based safety value functions to achieve provably safe, robust, and computationally efficient robot motion. We learn a Control Barrier Value Function (CBVF) from offline demonstration data using a model-free, finite-difference HJ recursion and deploy it as a real-time safety filter via a closed-form control law that modulates the DMP output. Unlike optimization-based CBF-QP approaches, our method achieves safety filtering without online quadratic program solves, preserving the computational efficiency of DMPs. We further incorporate an expectile-based offline learning objective that avoids querying out-of-distribution actions, and a conformal prediction calibration step that provides finite-sample probabilistic safety coverage. Experimental evaluation on a 7-DOF robot manipulator demonstrates that HJ-SafeDMP achieves formal safety guarantees with orders-of-magnitude faster execution than optimization-based baselines, while maintaining the robustness and adaptability of DMPs for human-robot interaction.

cs.RO↗

SurgXBench: Explainable Vision-Language Model Benchmark for Surgery

Innovations in digital intelligence are transforming robotic surgery with more informed decision-making. Real-time awareness of surgical instrument presence and actions (e.g., cutting tissue) is essential for such systems. Yet, despite decades of research, most machine learning models for this task are trained on small datasets and still struggle to generalize. Recently, vision-Language Models (VLMs) have brought transformative advances in reasoning across visual and textual modalities. Their unprecedented generalization capabilities suggest great potential for advancing intelligent robotic surgery. However, surgical VLMs remain under-explored, and existing models show limited performance, highlighting the need for benchmark studies to assess their capabilities and limitations and to inform future development. To this end, we benchmark the zero-shot performance of several advanced VLMs on two public robotic-assisted laparoscopic datasets for instrument and action classification. Beyond standard evaluation, we integrate explainable AI to visualize VLM attention and uncover causal explanations behind their predictions. This provides a previously underexplored perspective in this field for evaluating the reliability of model predictions. We also propose several explainability analysis-based metrics to complement standard evaluations. Our analysis reveals that surgical VLMs, despite domain-specific training, often rely on weak contextual cues rather than clinically relevant visual evidence, highlighting the need for stronger visual and reasoning supervision in surgical applications.

cs.CV↗

Probing chaos and thermalization through out-of-time-ordered correlators in random field spin chains

Out-of-time-ordered correlators (OTOCs) have emerged as a diagnostic of information scrambling and quantum chaos in many-body systems. We investigate the imprints of chaos in the dynamics of OTOCs in the Heisenberg spin-$1/2$ chain with random fields. The system is parameterized to exhibit a crossover from integrable to chaotic dynamics. We demonstrate numerically that the approach to saturation of the OTOC can distinguish between integrable and chaotic regimes, with a power-law $(1/t)$ relaxation for integrable systems and a higher-degree power-law decay $(1/t^α; α\ge 1)$ followed by an exponential relaxation for the chaotic regime. We further show that long-range spectral statistics, such as the number variance, are more effective in characterizing quantum chaos in the regime near saturation of OTOC. We also demonstrate that the relaxation and initial scrambling regimes exhibit distinct and universal features, with the former being sensitive and the latter being robust against different realizations of random-fields. The long-time saturation of OTOC also fluctuates with different realizations, and its exact expression is derived through the Eigenstate Thermalization Hypothesis.

quant-ph↗

Twisted conjugacy classes in Lie groups

We consider twisted conjugacy classes of continuous automorphisms $φ$ of a Lie group $G$. We obtain a necessary and sufficient condition on $φ$ for its Reidemeister number, the number of twisted conjugacy classes, to be infinite when $G$ is connected and solvable or compactly generated and nilpotent. We also show for a general connected Lie group $G$ that the number of conjugacy classes is infinite. We prove that for a connected non-nilpotent Lie group $G$, there exists $n\in \mathbb{N}$ such that Reidemeister number of $φ^n$ is infinite for every $φ$. We say that $G$ has topological $R_\infty$-property if the Reidemeister number of every $φ$ is infinite. We obtain conditions on a connected solvable Lie group under which it has topological $R_\infty$-property; which, in particular, enables us to prove that the group of invertible $n\times n$ upper triangular real matrices and its quotient group modulo its center have topological $R_\infty$-property for every $n\geq 2$. We also prove that the Walnut group also has this property. We show that ${\mathrm{SL}}(2,\mathbb{R})$ and ${\mathrm{GL}}(2,\mathbb{R})$ have topological $R_\infty$-property, and construct many examples of Lie groups with this property.

math.GR↗

PalpAid: Multimodal Pneumatic Tactile Sensor for Tissue Palpation

The tactile properties of tissue, such as elasticity and stiffness, often play an important role in surgical oncology when identifying tumors and pathological tissue boundaries. Though extremely valuable, robot-assisted surgery comes at the cost of reduced sensory information to the surgeon, with vision being the primary. Sensors proposed to overcome this sensory desert are often bulky, complex, and incompatible with the surgical workflow. We present PalpAid, a multimodal pneumatic tactile sensor to restore touch in robot-assisted surgery. PalpAid is equipped with a microphone and pressure sensor, converting contact force into an internal pressure differential. The pressure sensor acts as an event detector, while the acoustic signature assists in tissue identification. We show the design, fabrication, and assembly of sensory units with characterization tests for robustness to use, repetition cycles, and integration with a robotic system. Finally, we demonstrate the sensor's ability to classify 3D-printed hard objects with varying infills and soft ex vivo tissues. We envision PalpAid to be easily retrofitted with existing surgical/general robotic systems, allowing soft tissue palpation.

eess.SP↗