Assessing the Value of Visual Input: A Benchmark of Multimodal Large Language Models for Robotic Path Planning

Large Language Models (LLMs) show potential for enhancing robotic path planning. This paper assesses visual input's utility for multimodal LLMs in such tasks via a comprehensive benchmark. We evaluated 15 multimodal LLMs on generating valid and optimal paths in 2D grid environments, simulating simplified robotic planning, comparing text-only versus text-plus-visual inputs across varying model sizes and grid complexities. Our results indicate moderate success rates on simpler small grids, where visual input or few-shot text prompting offered some benefits. However, performance significantly degraded on larger grids, highlighting a scalability challenge. While larger models generally achieved higher average success, the visual modality was not universally dominant over well-structured text for these multimodal systems, and successful paths on simpler grids were generally of high quality. These results indicate current limitations in robust spatial reasoning, constraint adherence, and scalable multimodal integration, identifying areas for future LLM development in robotic path planning.

Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate

Large Language Models (LLMs) have demonstrated significant capabilities in understanding and generating human language, contributing to more natural interactions with complex systems. However, they face challenges such as ambiguity in user requests processed by LLMs. To address these challenges, this paper introduces and evaluates a multi-agent debate framework designed to enhance detection and resolution capabilities beyond single models. The framework consists of three LLM architectures (Llama3-8B, Gemma2-9B, and Mistral-7B variants) and a dataset with diverse ambiguities. The debate framework markedly enhanced the performance of Llama3-8B and Mistral-7B variants over their individual baselines, with Mistral-7B-led debates achieving a notable 76.7% success rate and proving particularly effective for complex ambiguities and efficient consensus. While acknowledging varying model responses to collaborative strategies, these findings underscore the debate framework's value as a targeted method for augmenting LLM capabilities. This work offers important insights for developing more robust and adaptive language understanding systems by showing how structured debates can lead to improved clarity in interactive systems.

LLM-based ambiguity detection in natural language instructions for collaborative surgical robots

Ambiguity in natural language instructions poses significant risks in safety-critical human-robot interaction, particularly in domains such as surgery. To address this, we propose a framework that uses Large Language Models (LLMs) for ambiguity detection specifically designed for collaborative surgical scenarios. Our method employs an ensemble of LLM evaluators, each configured with distinct prompting techniques to identify linguistic, contextual, procedural, and critical ambiguities. A chain-of-thought evaluator is included to systematically analyze instruction structure for potential issues. Individual evaluator assessments are synthesized through conformal prediction, which yields non-conformity scores based on comparison to a labeled calibration dataset. Evaluating Llama 3.2 11B and Gemma 3 12B, we observed classification accuracy exceeding 60% in differentiating ambiguous from unambiguous surgical instructions. Our approach improves the safety and reliability of human-robot collaboration in surgery by offering a mechanism to identify potentially ambiguous instructions before robot action.

Human-Robot collaboration in surgery: Advances and challenges towards autonomous surgical assistants

Human-robot collaboration in surgery represents a significant area of research, driven by the increasing capability of autonomous robotic systems to assist surgeons in complex procedures. This systematic review examines the advancements and persistent challenges in the development of autonomous surgical robotic assistants (ASARs), focusing specifically on scenarios where robots provide meaningful and active support to human surgeons. Adhering to the PRISMA guidelines, a comprehensive literature search was conducted across the IEEE Xplore, Scopus, and Web of Science databases, resulting in the selection of 32 studies for detailed analysis. Two primary collaborative setups were identified: teleoperation-based assistance and direct hands-on interaction. The findings reveal a growing research emphasis on ASARs, with predominant applications currently in endoscope guidance, alongside emerging progress in autonomous tool manipulation. Several key challenges hinder wider adoption, including the alignment of robotic actions with human surgeon preferences, the necessity for procedural awareness within autonomous systems, the establishment of seamless human-robot information exchange, and the complexities of skill acquisition in shared workspaces. This review synthesizes current trends, identifies critical limitations, and outlines future research directions essential to improve the reliability, safety, and effectiveness of human-robot collaboration in surgical environments.

Voice control interface for surgical robot assistants

Traditional control interfaces for robotic-assisted minimally invasive surgery impose a significant cognitive load on surgeons. To improve surgical efficiency, surgeon-robot collaboration capabilities, and reduce surgeon burden, we present a novel voice control interface for surgical robotic assistants. Our system integrates Whisper, state-of-the-art speech recognition, within the ROS framework to enable real-time interpretation and execution of voice commands for surgical manipulator control. The proposed system consists of a speech recognition module, an action mapping module, and a robot control module. Experimental results demonstrate the system's high accuracy and inference speed, and demonstrates its feasibility for surgical applications in a tissue triangulation task. Future work will focus on further improving its robustness and clinical applicability.

Embedded Image-to-Image Translation for Efficient Sim-to-Real Transfer in Learning-based Robot-Assisted Soft Manipulation

Recent advances in robotic learning in simulation have shown impressive results in accelerating learning complex manipulation skills. However, the sim-to-real gap, caused by discrepancies between simulation and reality, poses significant challenges for the effective deployment of autonomous surgical systems. We propose a novel approach utilizing image translation models to mitigate domain mismatches and facilitate efficient robot skill learning in a simulated environment. Our method involves the use of contrastive unpaired Image-to-image translation, allowing for the acquisition of embedded representations from these transformed images. Subsequently, these embeddings are used to improve the efficiency of training surgical manipulation models. We conducted experiments to evaluate the performance of our approach, demonstrating that it significantly enhances task success rates and reduces the steps required for task completion compared to traditional methods. The results indicate that our proposed system effectively bridges the sim-to-real gap, providing a robust framework for advancing the autonomy of surgical robots in minimally invasive procedures.

A hierarchical framework for collision avoidance in robot-assisted minimally invasive surgery

Minimally invasive surgery (MIS) procedures benefit significantly from robotic systems due to their improved precision and dexterity. However, ensuring safety in these dynamic and cluttered environments is an ongoing challenge. This paper proposes a novel hierarchical framework for collision avoidance in MIS. This framework integrates multiple tasks, including maintaining the Remote Center of Motion (RCM) constraint, tracking desired tool poses, avoiding collisions, optimizing manipulability, and adhering to joint limits. The proposed approach utilizes Hierarchical Quadratic Programming (HQP) to seamlessly manage these constraints while enabling smooth transitions between task priorities for collision avoidance. Experimental validation through simulated scenarios demonstrates the framework's robustness and effectiveness in handling diverse scenarios involving static and dynamic obstacles, as well as inter-tool collisions.

Enhancing the LLM-Based Robot Manipulation Through Human-Robot Collaboration

Large Language Models (LLMs) are gaining popularity in the field of robotics. However, LLM-based robots are limited to simple, repetitive motions due to the poor integration between language models, robots, and the environment. This paper proposes a novel approach to enhance the performance of LLM-based autonomous manipulation through Human-Robot Collaboration (HRC). The approach involves using a prompted GPT-4 language model to decompose high-level language commands into sequences of motions that can be executed by the robot. The system also employs a YOLO-based perception algorithm, providing visual cues to the LLM, which aids in planning feasible motions within the specific environment. Additionally, an HRC method is proposed by combining teleoperation and Dynamic Movement Primitives (DMP), allowing the LLM-based robot to learn from human guidance. Real-world experiments have been conducted using the Toyota Human Support Robot for manipulation tasks. The outcomes indicate that tasks requiring complex trajectory planning and reasoning over environments can be efficiently accomplished through the incorporation of human demonstrations.

Task segmentation based on transition state clustering for surgical robot assistance

Understanding surgical tasks represents an important challenge for autonomy in surgical robotic systems. To achieve this, we propose an online task segmentation framework that uses hierarchical transition state clustering to activate predefined robot assistance. Our approach involves performing a first clustering on visual features and a subsequent clustering on robot kinematic features for each visual cluster. This enables to capture relevant task transition information on each modality independently. The approach is implemented for a pick-and-place task commonly found in surgical training. The validation of the transition segmentation showed high accuracy and fast computation time. We have integrated the transition recognition module with predefined robot-assisted tool positioning. The complete framework has shown benefits in reducing task completion time and cognitive workload.

Constrained Motion Planning for a Robotic Endoscope Holder based on Hierarchical Quadratic Programming

Minimally Invasive Surgeries (MIS) are challenging for surgeons due to the limited field of view and constrained range of motion imposed by narrow access ports. These challenges can be addressed by robot-assisted endoscope systems which provide precise and stabilized positioning, as well as constrained and smooth motion control of the endoscope. In this work, we propose an online hierarchical optimization framework for visual servoing control of the endoscope in MIS. The framework prioritizes maintaining a remote-center-of-motion (RCM) constraint to prevent tissue damage, while a visual tracking task is defined as a secondary task to enable autonomous tracking of visual features of interest. We validated our approach using a 6-DOF Denso VS050 manipulator and achieved optimization solving times under 0.4 ms and maximum RCM deviation of approximately 0.4 mm. Our results demonstrate the effectiveness of the proposed approach in addressing the constrained motion planning challenges of MIS, enabling precise and autonomous endoscope positioning and visual tracking.