WO2025257246A1 - Prothèse de main robotique - Google Patents

Prothèse de main robotique

Info

Publication number
WO2025257246A1
WO2025257246A1 PCT/EP2025/066226 EP2025066226W WO2025257246A1 WO 2025257246 A1 WO2025257246 A1 WO 2025257246A1 EP 2025066226 W EP2025066226 W EP 2025066226W WO 2025257246 A1 WO2025257246 A1 WO 2025257246A1
Authority
WO
WIPO (PCT)
Prior art keywords
hand
camera
grip
prosthetic
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/EP2025/066226
Other languages
English (en)
Inventor
Dinar Amar JADHAV
Judi Nørtved SIMONSEN
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Merodz Aps
Original Assignee
Merodz Aps
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Merodz Aps filed Critical Merodz Aps
Publication of WO2025257246A1 publication Critical patent/WO2025257246A1/fr
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
    • A61F2/50—Prostheses not implantable in the body
    • A61F2/54—Artificial arms or hands or parts thereof
    • A61F2/58—Elbows; Wrists ; Other joints; Hands
    • A61F2/583—Hands; Wrist joints
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J15/00—Gripping heads and other end effectors
    • B25J15/0009—Gripping heads and other end effectors comprising multi-articulated fingers, e.g. resembling a human hand

Definitions

  • the present invention relates to robotic hand prostheses.
  • Robotic hand prostheses represent a beautiful blend of biomedicine, robotics, and artificial intelligence, aimed at restoring functionality and improving the quality of life for individuals with missing limbs. These advanced devices replicate the appearance and capabilities of a human hand through sophisticated engineering and technology.
  • robotic hand prostheses are their ability to grip and manipulate objects, which is central to many daily tasks. This capability is typically facilitated through the use of sensors and actuators that mimic the musculoskeletal structure of biological hands.
  • the operation of these prosthetic hands can be categorized mainly based on the source of control: myoelectric signals, brain-computer interfaces, or a combination of these technologies. Myoelectric control using residual limb muscles is currently the most prevalent method.
  • Myoelectric prostheses operate by detecting electrical signals from the user’s residual limb muscles.
  • the intended muscle contracts, producing a detectable electrical signal.
  • This signal is picked up by electrodes in the prosthetic socket, amplified, and then used to control the motors within the hand.
  • These motors actuate the fingers, allowing them to open and close around objects in a grip.
  • the strength and speed of the grip can often be adjusted, allowing for delicate tasks such as holding an egg or more robust needs such as gripping a tool.
  • Brain-computer interfaces (BCIs) represent a more advanced, albeit less common, approach. These systems directly tap into neural signals from the brain associated with intent to move the hand. These signals are then decoded by algorithms to determine the user’s intentions and translate them into movements of the robotic hand.
  • BCI technology is still largely experimental and not as widely available as myoelectric options.
  • Myoelectric prostheses are a major advancement in assistive technology, offering significant benefits for amputees, but they are not without their drawbacks.
  • One of the primary concerns reported by users revolves around the responsiveness of these devices, particularly in terms of the speed and fluidity of the gripping function.
  • the process from muscle contraction to actual movement of the hand involves several steps: detecting the muscle’s electrical activity, processing this signal to infer the user’s intent, and finally actuating the hand’s motors to perform the desired movement. Each of these steps introduces a slight delay.
  • the electrodes that detect electrical signals from the muscles can sometimes struggle to isolate the pertinent signals from background noise. This issue is compounded in environments where electrical interference is present or when the user’s residual limb experiences changes, such as swelling or shrinking, which can affect the fit of the socket and the placement of electrodes.
  • the algorithms that process these signals and translate them into actions must accurately interpret the user’s intent based on relatively noisy data. This computational interpretation is not instantaneous, which can result in a perceivable lag between the user’s muscle contraction and the prosthetic hand’s response.
  • the actuation mechanism itself may not be able to replicate the speed and fluidity of natural hand movements.
  • the motors used in prosthetic hands need to balance power, speed, durability, and battery life, often leading to compromises in performance. For instance, faster motors might consume more power, reducing the battery life of the prosthesis, or they might require making the hand heavier and less ergonomic.
  • This delay in response can be frustrating for users, particularly when performing tasks that require precise timing and coordination. It can also lead to a less intuitive and more cumbersome user experience, as individuals may need to consciously adjust their movements to sync with the slower response times of their prosthetic hands.
  • Adaptive Grasp Control through Multi-Modal Interactions for Assistive Prosthetic Devices describe a control system for prosthetic hands that incorporates multiple input modalities to facilitate adaptive grasping.
  • the system employs a Myo armband, which captures surface electromyography (sEMG) signals from the user’s residual limb. These signals are processed to classify gestures into a discrete set of predefined control commands.
  • Visual input is obtained through an RGB camera mounted in proximity to the prosthesis. The camera is used to detect objects in the surrounding environment, primarily through 2D bounding box recognition.
  • the architecture includes a touchscreen interface and a speech recognition module, allowing users to confirm or adjust proposed grasp actions.
  • Grasp selection in the system follows a semi-autonomous model: sensor inputs are used to generate grasp suggestions, which are then presented to the user for manual confirmation.
  • the gesture classification is based on an algorithm trained on discrete categories, and the system relies on user feedback to finalize grasp execution.
  • the system described by Esponda and Howard operates with 2D image data and does not perform 3D object modeling or pose estimation.
  • the visual processing is limited to planar object detection, and the overall control flow requires active user involvement in confirming grasp choices.
  • the authors present experimental results to demonstrate the feasibility of their approach in supporting user- adaptive prosthetic hand control within a semi-structured environment.
  • the robotic hand prosthesis of the present invention is capable, by identifying an object from a camera feed, to determine which grasping operation to use from a pre-defined list of different grasping operations.
  • the robotic hand prosthesis of the present invention can be programmed to switch between these grip types based on the user’s needs, thereby enhancing the usability and versatility of the prosthetic hand. Furthermore, as this is done automatically, rather than instructed by the user, the grasping operation is performed faster.
  • a first aspect relates to a robotic hand prosthesis operated by a user and configured to grip a target object, the robotic hand prostheses comprising:
  • a prosthetic socket comprising a sensor unit configured to detect electrical signals from the user’s residual limb muscles
  • an electromechanical hand mimicking the anatomical structure of a human hand, i.e., having a palm and multiple segmented fingers, said electromechanical hand comprising a motor controller operably connected to actuators;
  • the camera(s) is a depth camera configured for providing a real-time feed; said camera being positioned on the electromechanical hand such that it at all times points in the same direction as the direction of the electromechanical hand’s palm or the palmar surface of a finger; wherein the electromechanical hand further comprises: - a first processor operably connected to said camera and said sensor unit;
  • the first memory comprises program instructions executable by the first processor for: i) receiving image data streams from said camera(s); ii) receiving signaling data from said sensor unit based on electrical signals from the user’s residual limb muscles; iii) processing received signaling data from said sensor unit as an instruction to perform a grasping operation; iv) processing received image data from the camera to identify an object to be grasped; v) utilizing said identified object to determine which grasping operation to use from a pre-defined list of different grasping operations; and vi) instructing the electromechanical hand’s motor controller to perform said selected grasping operation.
  • robot hand prosthesis and “prosthetic hand” will be used interchangeably throughout the application.
  • Figure 1 shows a robotic hand prosthesis according to the present invention.
  • the present invention offers a more tightly integrated and fully autonomous prosthetic control architecture that improves responsiveness, usability, and precision in grasp execution.
  • Esponda and Howard employ a semi-automated system relying on an external Myo armband, discrete gesture classification, and manual user confirmation via touchscreen or speech input
  • the present system incorporates a sensor unit directly into the prosthetic socket. This integration allows for direct acquisition of electromyographic signals from the user’s residual limb, resulting in a more stable, robust, and low-latency input pathway for interpreting user intent.
  • the present system utilizes a depth camera that is physically mounted on the electromechanical hand in a manner that ensures it is aligned with the palm or the palmar surface of a finger. This orientation guarantees that the camera’s field of view closely matches the grasp direction, significantly enhancing the accuracy of object localization and the relevance of visual data used for grasp planning.
  • the control pipeline is further distinguished by its ability to operate in a fully autonomous manner.
  • the system Upon detecting a user command via EMG signals, the system is configured to process visual input from the depth camera to identify a target object, determine an appropriate grasp type from a predefined set, and execute the grasp automatically, without requiring user confirmation.
  • This realtime, end-to-end perception-to-actuation process reduces cognitive burden on the user and supports more natural, intuitive prosthetic control.
  • the present system addresses several limitations of prior art solutions. It eliminates the need for manual grasp confirmation, enables more context-sensitive and accurate grasping actions, and enhances overall system responsiveness. These improvements are particularly advantageous in real-world, unstructured environments where speed, reliability, and intuitive operation are essential for effective prosthesis use.
  • a first aspect relates to a robotic hand prosthesis operated by a user and configured to grip a target object, the robotic hand prostheses comprising:
  • a prosthetic socket comprising a sensor unit configured to detect electrical signals from the user’s residual limb muscles
  • an electromechanical hand mimicking the anatomical structure of a human hand, i.e., having a palm and multiple segmented fingers, said electromechanical hand comprising a motor controller operably connected to actuators;
  • the camera(s) is a depth camera configured for providing a real-time feed; said camera being positioned on the electromechanical hand such that it at all times points in the same direction as the direction of the electromechanical hand’s palm or the palmar surface of a finger; wherein the electromechanical hand further comprises:
  • the first memory comprises program instructions executable by the first processor for: i) receiving image data streams from said camera(s); ii) receiving signaling data from said sensor unit based on electrical signals from the user’s residual limb muscles; iii) processing received signaling data from said sensor unit as an instruction to perform a grasping operation; iv) processing received image data from the camera to identify an object to be grasped; v) utilizing said identified object to determine which grasping operation to use from a pre-defined list of different grasping operations; and vi) instructing the electromechanical hand’s motor controller to perform said selected grasping operation.
  • the prosthetic socket is an essential component of the robotic hand prosthesis, as it serves as the interface between the user’s residual limb and the mechanical parts of the device. Its primary role is to ensure that the prosthesis is securely and comfortably attached, which is critical for both the functionality and control of the limb.
  • the socket may be custom fitted to the user’s residual limb, a process that typically involves casting the limb to create a precise mold. This mold is then used to manufacture the socket using materials, such as lightweight thermoplastics or composites, which are chosen for their durability and comfort. It may even be 3D-printed.
  • Integrating sensors into the prosthetic socket enables the prosthesis to interact more effectively with the user and respond dynamically to external conditions.
  • Various types of sensors may be used, each serving a specific function.
  • Pressure sensors for instance, measure the distribution and intensity of pressure exerted by the residual limb against the socket walls, providing essential data for adjusting the fit and enhancing comfort.
  • EMG electromyographic
  • sensors such as those measuring temperature and humidity monitor the microclimate inside the socket, helping to prevent skin irritation and other complications related to heat and moisture.
  • Motion sensors including accelerometers and gyroscopes, track the orientation and movements of the residual limb, refining the algorithms that translate these movements into mechanical actions of the prosthetic hand.
  • the prosthetic socket is far from a passive structural element. It is a critical active component that significantly improves the prosthetic’s functionality, safety, and user comfort.
  • the electromechanical hand replicates the functionality and appearance of a human hand through a blend of electronic and mechanical engineering.
  • This part of the prosthesis comprises articulated fingers and a thumb, each equipped with multiple joints that mimic the natural articulation points found in human hands, such as the metacarpophalangeal (MCP), proximal interphalangeal (PIP), and distal interphalangeal (DIP) joints.
  • MCP metacarpophalangeal
  • PIP proximal interphalangeal
  • DIP distal interphalangeal
  • the thumb typically features fewer joints to facilitate its unique opposition capability, which is essential for executing a range of gripping actions.
  • Actuators are integral to the function of the electromechanical hand, serving as substitutes for muscles. These are most commonly small electric motors embedded within the hand or wrist, though other technologies, such as pneumatic or hydraulic systems, or shape memory alloys, may also be employed. These actuators drive the movement of the fingers, allowing for both individual and coordinated group movements across the fingers depending on the complexity of the design. The choice of actuator affects not only the performance of the prosthetic hand but also its usability, weight, and power requirements. Electric motors are favored for their balance of size, power, and reliability. In a typical setup, signals from the user’s muscle contractions are processed by the prosthetic’s control system and translated into specific movements via the actuators.
  • the design preferably includes feedback mechanisms, either through direct sensory feedback or visual cues, allowing a user to adjust their grip based on the task at hand.
  • These motors can be configured to drive the fingers individually or in groups depending on the design of the hand. The motors often operate through gear systems that magnify their torque, allowing the fingers to open and close with enough strength to perform tasks ranging from lifting heavy items to holding delicate objects securely without causing damage.
  • Control over these actuators is achieved through input signals derived from electromyographic (EMG) sensors placed along the user’s residual limb.
  • EMG electromyographic
  • controller such as a microcontroller or a processor, within the prosthesis, which uses programmed algorithms to translate the signals into specific, finely tuned movements.
  • Sensor integration further enhances the functionality of the electromechanical hand.
  • Tactile sensors located on the fingertips or palm help the hand adjust its grip based on the physical properties of the objects it encounters, such as pressure and texture.
  • Advanced tactile sensors use vibration to assess surface texture. The sensor induces a vibration upon contact with the surface and measures the response. Smooth surfaces tend to have less damping and a clearer vibrational profile.
  • Position sensors within the joints provide critical feedback on the positioning of the fingers, enabling precise control over the hand’s movements.
  • Modern prosthetic hands may include systems that provide the user with sensory feedback related to grip force and object contact. This feedback can be conveyed through various means, including vibrations or small electrical impulses, simulating the natural feedback one would receive from a biological hand.
  • the overall integration of the electromechanical hand with the prosthetic limb and the user’s body is crucial for effective function. This typically involves a connection to a rotational wrist unit and a forearm section that leads up to the custom-fitted socket, ensuring seamless mechanical and aesthetic integration.
  • the external appearance of the hand is often enhanced with a glove-like covering that mimic human skin, helping to make the mechanical parts appear more natural.
  • the electromechanical hand in a prosthetic device embodies a remarkable convergence of technology and human biomechanics, designed to restore functionality, and improve the quality of life for users. Advances in materials, sensor technology, and control systems continue to push the boundaries of what these prosthetic hands can achieve, making them more intuitive and effective for everyday use.
  • the term “grasping operation” refers to specific technical terms that describe the mechanics and objectives of each grip type.
  • a starting configuration prior to a grasping operation of the robotic hand prosthesis may be seen in Figure 1 , where the camera’s view is unobstructed by the finger positions.
  • the camera 110 is integrated into the palm 120 of the robotic hand prosthesis 100.
  • Power Grip This grasp is used when force is required, involving the whole hand to enclose and hold an object.
  • the fingers excluding the thumb
  • the palm work together to wrap around and secure the object, as seen in holding a hammer or a steering wheel.
  • Precision Grip In contrast to the power grip, the precision grip is used for fine manipulation of objects, involving the tips of the fingers and the thumb. It allows for delicate handling and precise movements, typical in tasks like writing with a pen or threading a needle.
  • Pinch Grip This is a form of precision grip that uses the thumb in opposition to one or more fingers to hold an object.
  • a tip pinch is shown in Figure 2, where the thumb 130 and index finger 140 of the robotic hand prosthesis 100 are used.
  • the pinch grip may be subdivided into different types: Tip Pinch: Using the tips of the thumb and one finger to grasp an object, like picking up a small bead.
  • Palmar Pinch (or three-jaw chuck): The thumb, index, and middle fingers come together to hold an object, useful for tasks such as holding a key or a credit card. Lateral Pinch (or key pinch): Where the object is pinched between the side of the index finger and the thumb, resembling holding a key to turn it in a lock.
  • Hook Grip This grip involves the fingers primarily, often without substantial thumb involvement. It is used for carrying bags with handles or hoisting a bucket. The load is supported by the fingers bending at the knuckles, and the palm usually does not participate.
  • Spherical Grip This involves holding round objects like a ball, where the fingers and thumb are positioned around the object in a spherical formation.
  • Cylindrical Grip Used for holding tube-shaped items like a drinking glass or a doorknob, this grip engages the fingers wrapped around the object and the thumb used for opposition.
  • Each of these grasping types is important in prosthetic design as they correspond to everyday tasks that users need to perform.
  • the robotic hand prosthesis of the present invention can be programmed to switch between these grip types based on the user’s needs, thereby enhancing the usability and versatility of the prosthetic hand.
  • the grasping operation is performed faster.
  • myoelectric prostheses represent a significant advancement in prosthetic technology, utilizing the electrical activity generated by muscle contractions in the residual limb to control the movements of a prosthetic hand. This process involves several sophisticated steps that seamlessly integrate hardware and software to create a functional extension of the human body.
  • EMG electromyographic
  • the refined signals are mapped to the specific actions of the prosthetic hand.
  • the different types of grips are automatically evaluated by the robotic hand prosthesis of the present invention and will thus not need to be learned in this way.
  • the mapping is crucial and involves a calibration phase where users learn to control their muscle contractions to produce reliable and repeatable actions. This phase may also involve adaptive algorithms that learn from the user’s muscle activity patterns, improving the interface’s responsiveness and intuitiveness over time.
  • the final step in the command process is the activation of the prosthetic’s actuators.
  • These components which include motors and joints, are responsible for executing the movements that result in the desired grip. For instance, contracting specific muscles might cause the hand to execute a grasping function, while other contractions lead to a release of the grasping function (i.e., to release an object).
  • Feedback mechanisms may be incorporated that can provide the user with tactile or other forms of feedback regarding the force applied or the position of the prosthetic fingers, which is invaluable for making real-time adjustments to the grip.
  • the first processor is equipped with artificial intelligence for enhancing object recognition and/or adaptive gripping.
  • This application of artificial intelligence enables the prosthetic hand to interact intelligently with its environment, beyond merely responding to user commands.
  • Artificial intelligence algorithms may be configured to analyze the camera’s realtime feed data to determine the most appropriate grip type for each object.
  • the prosthetic hand can adjust its grip to handle a delicate object like an egg with gentle pressure or grasp a sturdy object like a hammer with greater force.
  • these intelligent systems may be configured to learn from past interactions, which improves the prosthetic’s performance over time. This learning process allows the device to adapt to the user’s specific preferences and movements, as well as to optimize its responses for more efficient and effective object manipulation. Artificial intelligence algorithms may also be configured to assist in making autonomous decisions about how to interact with objects, which is especially useful in scenarios where the user might not be able to provide clear or strong muscle signals. Integrating cameras as sensors in the prosthetic hand according to the present invention enhances the functionality and usability of the device by providing a natural perspective for object interaction. The camera is positioned on the electromechanical hand such that it always points in the same direction as the direction of the electromechanical hand’s palm or the palmar surface of a finger.
  • Positioning cameras on or into the palm is advantageous because it aligns with how a human hand typically views and approaches objects. This placement allows the camera to capture detailed visual information about an object’s size, shape, and orientation just as the hand moves to grasp it, facilitating accurate and adaptive grip adjustments.
  • Embedding cameras in the palm also ensures that they are well-integrated within the hand’s structure, offering protection from damage and maintaining the prosthetic’s aesthetic integrity. This setup avoids the addition of protruding elements that could interfere with daily activities by catching on clothing or impeding movement. Moreover, a palm-mounted camera focuses precisely on the area where object manipulation occurs, capturing essential details about the object’s texture and material properties that are crucial for nuanced gripping strategies.
  • the implementation of camera technology requires careful consideration of several factors.
  • the camera should preferably have sufficient resolution and sensitivity to function effectively under various lighting conditions.
  • the camera should also be capable of fast response times to support real-time processing, a necessity for dynamic and responsive prosthetic movements.
  • the choice of lens is of importance, as it must provide the necessary field of view without causing distortive effects that could disrupt the processing algorithms.
  • Integrating a depth camera into the prosthetic hand significantly enhances its functionality by providing three-dimensional information about the environment. This capability allows the prosthetic to accurately assess the size, shape, and orientation of objects, which is crucial for adapting the grip accordingly.
  • Depth cameras capture the distance between the camera and the objects in its view, offering a precise understanding of each object’s physical characteristics. This precision enables the prosthetic hand to adjust its fingers for optimal contact, ensuring a secure yet gentle grip that minimizes the risk of damage or dropping the object.
  • a depth camera also improves the prosthetic hand’s spatial awareness, aiding in navigating complex environments. This enhanced spatial understanding helps the user perform tasks more efficiently and safely, as the prosthetic can avoid unwanted collisions and better judge when to close or open the hand. Additionally, depth cameras facilitate more autonomous actions, such as reaching out and grasping objects without precise user-directed control, which is particularly beneficial for users with limited mobility or muscle strength.
  • Depth cameras also offer advantages in handling transparent or highly reflective objects. Unlike standard cameras, which can struggle with light distortion or reflections, depth cameras use technologies like infrared light to measure distances, allowing for more reliable detection of these challenging objects.
  • the depth camera is an RGB depth camera.
  • RGB depth camera which merges standard RGB (Red, Green, Blue) color imaging with depth sensing, is particularly suitable for prosthetic hand applications because it provides a rich blend of visual and spatial data.
  • RGB Red, Green, Blue
  • This dual capability allows the prosthetic hand to perceive and interpret the world much like a human does, offering detailed insights into both the appearance and the spatial arrangement of objects.
  • Such cameras deliver comprehensive perception, enabling the prosthetic to identify and distinguish objects based on a wide array of characteristics, including shape, size, color, and texture.
  • the combination of color and depth information greatly enhances the prosthetic’s object recognition capabilities.
  • Color data assists in recognizing subtle visual details such as color patterns and surface textures, which are crucial for distinguishing between items that may appear similar in shape but differ significantly in other attributes.
  • Depth information complements this by providing accurate spatial orientation and size measurements, which helps the prosthetic tailor its grip and manipulation strategies accordingly.
  • an RGB depth camera improves how the prosthetic hand interacts with its environment. It enables the hand to navigate complex settings more effectively and interact with objects in sophisticated ways, such as adjusting its grip based on the object’s perceived weight and fragility or performing intricate tasks that require fine motor skills. This level of interaction is particularly important in scenarios where precision is crucial, such as handling delicate or potentially hazardous materials.
  • This technology not only improves the user experience by providing an intuitive and responsive interface but also supports a wider range of activities. Users can engage more confidently in diverse tasks, supported by the prosthetic's ability to handle complex visual scenes.
  • RGB depth cameras can be used to provide feedback to the user, aiding them in mastering the use of the prosthetic. It also facilitates continuous learning and improvement of the prosthetic’s performance through machine learning algorithms, which adjust and optimize its functionality based on accumulated experiences.
  • RGB depth camera within a prosthetic hand significantly enhances its capability to mimic human sensory and cognitive processes.
  • This advanced technology not only makes the prosthetic hand a powerful tool but also a genuine extension of the human body, expanding the user’s abilities and independence in daily life.
  • Providing a real-time camera feed for the prosthetic hand provides substantial advantages, enhancing both the functionality and responsiveness of the device. This capability is crucial for allowing the prosthetic hand to interact dynamically with its environment, adjusting promptly to changes as they occur.
  • the immediate feedback from a real-time camera ensures that the prosthetic hand can respond quickly, facilitating smoother and more natural interactions similar to those of a biological hand.
  • a real-time camera feed also facilitates a higher degree of autonomy in the prosthetic hand, allowing it to perform certain actions independently, such as automatically adjusting its position to provide a better catch on a slipping object. This immediacy is essential for enabling the hand to make split-second decisions based on the visual data it receives.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Orthopedic Medicine & Surgery (AREA)
  • Transplantation (AREA)
  • Biomedical Technology (AREA)
  • Mechanical Engineering (AREA)
  • Cardiology (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Robotics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Vascular Medicine (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Prostheses (AREA)

Abstract

La présente invention concerne une prothèse de main robotique capable de déterminer quelle opération de préhension doit être utilisée à partir d'une liste prédéfinie de différentes opérations de préhension par identification d'un objet à partir d'un flux de caméra.
PCT/EP2025/066226 2024-06-11 2025-06-11 Prothèse de main robotique Pending WO2025257246A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP24181344.3 2024-06-11
EP24181344 2024-06-11

Publications (1)

Publication Number Publication Date
WO2025257246A1 true WO2025257246A1 (fr) 2025-12-18

Family

ID=91481620

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2025/066226 Pending WO2025257246A1 (fr) 2024-06-11 2025-06-11 Prothèse de main robotique

Country Status (1)

Country Link
WO (1) WO2025257246A1 (fr)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108742957A (zh) * 2018-06-22 2018-11-06 上海交通大学 一种多传感融合的假肢控制方法
GB2574596A (en) * 2018-06-08 2019-12-18 Epic Inventing Inc Prosthetic device
KR102582861B1 (ko) * 2021-07-15 2023-09-27 중앙대학교 산학협력단 카메라와 레이저를 이용하여 사물 자율인식이 가능한 전자의수 및 그 작동방법

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2574596A (en) * 2018-06-08 2019-12-18 Epic Inventing Inc Prosthetic device
CN108742957A (zh) * 2018-06-22 2018-11-06 上海交通大学 一种多传感融合的假肢控制方法
KR102582861B1 (ko) * 2021-07-15 2023-09-27 중앙대학교 산학협력단 카메라와 레이저를 이용하여 사물 자율인식이 가능한 전자의수 및 그 작동방법

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
MICHELLE ESPONDA ET AL: "Adaptive Grasp Control through Multi-Modal Interactions for Assistive Prosthetic Devices", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 18 October 2018 (2018-10-18), XP080925045 *
MICHELLE ESPONDA ET AL: "Adaptive Grasp Control through Multi-Modal Interactions for Assistive Prosthetic Devices", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 18 October 2018 (2018-10-18), XP081067365 *

Similar Documents

Publication Publication Date Title
Mouchoux et al. Artificial perception and semiautonomous control in myoelectric hand prostheses increases performance and decreases effort
Starke et al. Semi-autonomous control of prosthetic hands based on multimodal sensing, human grasp demonstration and user intention
JP6389191B2 (ja) 義手システム
Wu et al. “Hold-and-manipulate” with a single hand being assisted by wearable extra fingers
EP2865356A1 (fr) Prothèse de main hybride
CN107127735A (zh) 人示范式具有力与位置目的任务的机器人学习
CN1785608A (zh) 多指机械灵巧手闭环实时动作控制平台
CN211362244U (zh) 一种基于外骨骼数据手套和肌电手环的遥操作系统
Kulkarni et al. Overview: mechanism and control of a prosthetic arm
Zhang et al. Biomechatronic design and control of an anthropomorphic artificial hand for prosthetic applications
CN115252240A (zh) 一种人在环路的上臂假肢半自主灵巧控制系统
CN113509298A (zh) 一种基于振动的假肢手力位信息反馈系统及方法
Zhang et al. Design and control of a multisensory five-finger prosthetic hand
JPH09109069A (ja) パワード・インテリジェント方法及びユニット
Gurav et al. Innovative prosthetic hand design: Integrating EMG sensors and 3D printing for enhanced usability
Yang et al. Fingertip proximity-based grasping pattern prediction of transradial myoelectric prosthesis
JP6431284B2 (ja) 過剰人工付属肢を用いて人間の手の機能を拡張する装置及び方法
WO2025257246A1 (fr) Prothèse de main robotique
KR102326552B1 (ko) 근전 전동의수의 엄지와 검지기반 손동작 제어시스템 및 그 제어방법
Matrone et al. Bio-inspired controller for a dexterous prosthetic hand based on principal components analysis
James et al. Realtime hand landmark tracking to aid development of a prosthetic arm for reach and grasp motions
Zheng et al. A prosthetic hand system with human-like grasping by combining EMG and visual information
Castellini et al. Gaze tracking for robotic control in intelligent teleoperation and prosthetics
Das et al. Advancing neural engineering: Hierarchical control strategies with human-centered focus for hand prosthetics
Choudhury et al. An effective optimization of EMG based artificial prosthetic limbs

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 25732422

Country of ref document: EP

Kind code of ref document: A1