人工智能如何帮助机器人媲美灵巧的人手？
正文翻译
The human hand is one of the most staggeringly sophisticated and physiologically intricate parts of the body. It has more than 30 muscles, 27 joints alongside a network of ligaments and tendons that give it 27 degrees of freedom. There are more than 17,000 touch receptors and nerve endings in the palm alone. These features allow our hands to perform a dazzling array of highly complex tasks through a broad range of different movements.
人手是人体中最精密、生理构造最复杂的部位之一。人手由30多块肌肉、27个关节、以及韧带和肌腱网络构成，使其具有27个自由度。仅手掌就有17000多个触觉感受器和神经末梢。这些特征使我们的双手做出各种不同的动作，从而执行数不胜数、非常复杂的任务。
The human hand is one of the most staggeringly sophisticated and physiologically intricate parts of the body. It has more than 30 muscles, 27 joints alongside a network of ligaments and tendons that give it 27 degrees of freedom. There are more than 17,000 touch receptors and nerve endings in the palm alone. These features allow our hands to perform a dazzling array of highly complex tasks through a broad range of different movements.
人手是人体中最精密、生理构造最复杂的部位之一。人手由30多块肌肉、27个关节、以及韧带和肌腱网络构成，使其具有27个自由度。仅手掌就有17000多个触觉感受器和神经末梢。这些特征使我们的双手做出各种不同的动作，从而执行数不胜数、非常复杂的任务。
But you don't need to tell any of that to Sarah de Lagarde.
但是，你没必要让莎拉·德拉加德知道这些了。
但是，你没必要让莎拉·德拉加德知道这些了。
In August 2022, she was on top of the world. She had just climbed Mount Kilimanjaro with her husband and was supremely fit. But just one month later, she found herself lying in a hospital bed, with horrific injuries.
2022年8月，她处于人生的巅峰状态。她刚刚与丈夫一起成功攀登了乞力马扎罗山，身体状况极佳。但仅仅一个月后，她发现自己躺在病床上，伤势严重。
2022年8月，她处于人生的巅峰状态。她刚刚与丈夫一起成功攀登了乞力马扎罗山，身体状况极佳。但仅仅一个月后，她发现自己躺在病床上，伤势严重。
While returning home from work, De Lagarde slipped and fell between a tube train and the platform at High Barnet station in London. Crushed by the departing train and another that then came into the station, she lost her right arm below the shoulder and part of her right leg.
德拉加德在下班回家途中，在伦敦的高巴尼特站滑倒跌入站台与地铁的缝隙中，先后被离站和进站的地铁碾压，失去了整条右臂和部分右腿。
德拉加德在下班回家途中，在伦敦的高巴尼特站滑倒跌入站台与地铁的缝隙中，先后被离站和进站的地铁碾压，失去了整条右臂和部分右腿。
After the long healing process, she was offered a prosthetic arm by the UK's National Health Service, but it offered her little in terms of normal hand movement. Instead, it seemed to prioritise form over functionality.
在经过漫长的康复治疗后，英国国民医疗服务体系为她安装了一个假肢，但对于实现手部的正常活动没什么帮助，似乎形式大于实用性。
在经过漫长的康复治疗后，英国国民医疗服务体系为她安装了一个假肢，但对于实现手部的正常活动没什么帮助，似乎形式大于实用性。
"It doesn't really look like a real arm," she says. "It was deemed creepy by my children."
她说：“假肢看起来并不像真实的手臂，我的孩子们看到它会感到害怕”。
她说：“假肢看起来并不像真实的手臂，我的孩子们看到它会感到害怕”。
The prosthetic only featured a single joint at the elbow while the hand itself was a static mass on the end. For nine months she struggled to perform the daily tasks she had previously taken for granted, but then was offered something transformational – a battery-powered bionic arm utilising artificial intelligence (AI) to anticipate the movements she wants by detecting tiny electrical signals from her muscles.
这种假肢只有一个肘关节，其末端的手是固定不动的。在九个月的时间里，她一直在艰难地完成以前习以为常的日常工作，但后来用上了变革性的产品——电池供电的仿生手臂，它利用人工智能来捕捉微弱的肌电信号，以此预测她想做出的动作。
这种假肢只有一个肘关节，其末端的手是固定不动的。在九个月的时间里，她一直在艰难地完成以前习以为常的日常工作，但后来用上了变革性的产品——电池供电的仿生手臂，它利用人工智能来捕捉微弱的肌电信号，以此预测她想做出的动作。
"Every time I make a movement it learns," De Lagarde says. "The machine learns to recognise the patterns and eventually it turns into generative AI, where it starts predicting what my next move is."
“每当我做出动作时，它都会学习”，德拉加德说道。“仿生手臂学习识别我的动作模式，最终转变成生成性人工智能，以此来预测我的下一个动作”。
“每当我做出动作时，它都会学习”，德拉加德说道。“仿生手臂学习识别我的动作模式，最终转变成生成性人工智能，以此来预测我的下一个动作”。
Even picking up something as simple as a pen, and fiddling it in our fingers to adopt a writing position involves seamless integration between body and brain. Hand-based tasks that we perform with barely a thought require a refined combination of both motor control and sensory feedback – from opening a door to playing a piano.
就连捡起钢笔这种简单的物体，手指调整成握笔姿势，都需要人体与大脑之间的无缝整合。我们的双手不假思索地执行任务，这需要运动控制与感觉反馈的精确结合，开门或弹钢琴也是如此。
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
就连捡起钢笔这种简单的物体，手指调整成握笔姿势，都需要人体与大脑之间的无缝整合。我们的双手不假思索地执行任务，这需要运动控制与感觉反馈的精确结合，开门或弹钢琴也是如此。
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
With this level of complexity, it's no wonder that attempts to match the versatility and dexterity of human hands have evaded medical professionals and engineers alike for centuries. From the rudimentary spring-loaded iron hand of a 16th-Century German knight to the world's first robotic hand with sensory feedback created in 1960s Yugoslavia, nothing has come close to matching the natural abilities of the human hand. Until now.
人手这么复杂，难怪几个世纪以来，医学专家和工程师们制造不出在功能和灵巧方面堪比人手的机械装置。从16世纪德国骑士使用的装有弹簧的简陋铁手，到20世纪60年代南斯拉夫发明的世界上第一只具有感觉反馈能力的机械手，人手与生俱来的能力始终无与伦比，直到现在依然如此。
人手这么复杂，难怪几个世纪以来，医学专家和工程师们制造不出在功能和灵巧方面堪比人手的机械装置。从16世纪德国骑士使用的装有弹簧的简陋铁手，到20世纪60年代南斯拉夫发明的世界上第一只具有感觉反馈能力的机械手，人手与生俱来的能力始终无与伦比，直到现在依然如此。
Advances in AI are ushering in a generation of machines that are getting close to matching human dexterity. Intelligent prostheses, like the one De Lagarde received, can anticipate and refine movement. Soft-fruit picking bots can pluck a strawberry in a field and place it delicately in a punnet of other berries without squishing them. Vision-guided robots can even carefully extract nuclear waste from reactors. But can they really ever compete with the amazing capabilities of the human hand?
人工智能的进步催生出在灵巧方面不断接近人类的新一代机械装置。例如，德拉加德使用的智能假肢能够预测和完善她的动作。软果采摘机器人在农田里采摘一只草莓，将其小心翼翼地放入盛有其他浆果的果篮中，而不会把它们压扁。视觉引导机器人甚至能够小心地从反应堆中提取核废料。但是它们真能比得上能力非凡的人手吗？
人工智能的进步催生出在灵巧方面不断接近人类的新一代机械装置。例如，德拉加德使用的智能假肢能够预测和完善她的动作。软果采摘机器人在农田里采摘一只草莓，将其小心翼翼地放入盛有其他浆果的果篮中，而不会把它们压扁。视觉引导机器人甚至能够小心地从反应堆中提取核废料。但是它们真能比得上能力非凡的人手吗？
Embodied AI
具身智能
具身智能
I recently gave birth to my first child. Within moments of entering the world, my daughter's small hand wrapped softly around my partner's forefinger. Unable to focus her eyes on anything more than a few inches in front of her, her hand and arm movements are limited, on the whole, to involuntary reflexes that allow her to grip an obxt when it is placed in her palm. It is an adorable illustration of the sensitivity of our dexterity, even in our earliest moments – and hints at how much it improves as we mature.
我最近生下第一个孩子。女儿刚来到这个世界时，小手轻轻地握住了我对象的食指。由于她看不清楚几英寸以外的任何物体，手和手臂的动作基本出于无意识的反射，使她能够抓取手心的物体。这可爱的一幕生动展现了我们在生命之初就已具备灵敏的触觉，也预示着我们成年后，这种能力有多么大的提升。
我最近生下第一个孩子。女儿刚来到这个世界时，小手轻轻地握住了我对象的食指。由于她看不清楚几英寸以外的任何物体，手和手臂的动作基本出于无意识的反射，使她能够抓取手心的物体。这可爱的一幕生动展现了我们在生命之初就已具备灵敏的触觉，也预示着我们成年后，这种能力有多么大的提升。
Over the coming months, my daughter's vision will progress enough to give her depth perception, while the motor cortex of her brain will develop, giving her increasing control over her limbs. Her involuntary grasps will give way to more deliberate grabbing actions, her hands feeding signals back to her brain, allowing her to make fine adjustments in movement as she feels and explores the world around her. It will take my daughter several years of determined effort, trial, error and play to attain the level of hand dexterity that adults possess.
在接下来的几个月里，我女儿视觉的改善足以让她具备深度知觉，大脑运动皮层的发育将增强她对四肢的控制力。她的无意识抓取将被有意识抓取所取代，她的手将向大脑反馈信号，使她在感知和探索周围的世界时调整自己的动作。我女儿需要多年的努力、试错、游戏，才能达到成年人的手所具有的灵巧度。
在接下来的几个月里，我女儿视觉的改善足以让她具备深度知觉，大脑运动皮层的发育将增强她对四肢的控制力。她的无意识抓取将被有意识抓取所取代，她的手将向大脑反馈信号，使她在感知和探索周围的世界时调整自己的动作。我女儿需要多年的努力、试错、游戏，才能达到成年人的手所具有的灵巧度。
And much like a baby learning how to use their hands, dexterous robots utilising embodied AI follow a similar roadmap. Such robots must co-exist with humans in an environment, and learn how to carry out physical tasks based on prior experience. They react to their environment and fine-tune their movements in response to such interactions. Trial and error plays a big part in this process.
就像婴儿学习如何使用双手一样，采用具身智能技术的灵巧机器人会遵循类似的成长路径。这种机器人一定会与人类在环境中共存，学习如何根据先前的经验来执行体力任务。他们会对周围环境做出反应，并根据这种互动调整自己的动作，试错在这一过程中起着重要作用。
就像婴儿学习如何使用双手一样，采用具身智能技术的灵巧机器人会遵循类似的成长路径。这种机器人一定会与人类在环境中共存，学习如何根据先前的经验来执行体力任务。他们会对周围环境做出反应，并根据这种互动调整自己的动作，试错在这一过程中起着重要作用。
"Traditional AI handles information, while embodied AI perceives, understands, and reacts to the physical world," says Eric Jing Du, professor of civil engineering at the University of Florida. "It essentially endows robots with the ability to 'see' and 'feel' their surrounding environments, enabling them to perform actions in a human-like manner."
佛罗里达大学土木工程系教授埃里克·杜晶表示：“传统的人工智能处理信息，而具身智能感知、理解物理世界，并对此做出反应。具身智能从根本上赋予机器人‘观察’和‘感知’周围世界的能力，使他们能够以人类的方式行动”。
佛罗里达大学土木工程系教授埃里克·杜晶表示：“传统的人工智能处理信息，而具身智能感知、理解物理世界，并对此做出反应。具身智能从根本上赋予机器人‘观察’和‘感知’周围世界的能力，使他们能够以人类的方式行动”。
But this technology is still in its infancy. Human sensory systems are so complex and our perceptive abilities so adept that reproducing dexterity at the same level as the human hand remains a formidable challenge.
但是，这项技术仍处于起步阶段。由于人类的感觉系统十分复杂，我们的感知能力十分发达，因此再现与人手同样的灵巧能力仍然是个严峻的挑战。
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
但是，这项技术仍处于起步阶段。由于人类的感觉系统十分复杂，我们的感知能力十分发达，因此再现与人手同样的灵巧能力仍然是个严峻的挑战。
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
"Human sensory systems can detect minute changes, and rapidly adapt to changes in tasks and environments," says Du. "They integrate multiple sensory inputs like vision, touch and temperature. Robots currently lack this level of integrated sensory perception."
杜教授说：“人类的感觉系统能够觉察到细微的变化，并迅速适应任务和环境中的变化。人类的感觉系统整合了视觉、触觉、温度等多种感觉信息。机器人目前尚不具备这么先进的感官知觉整合能力”。
杜教授说：“人类的感觉系统能够觉察到细微的变化，并迅速适应任务和环境中的变化。人类的感觉系统整合了视觉、触觉、温度等多种感觉信息。机器人目前尚不具备这么先进的感官知觉整合能力”。
But the level of sophistication is rapidly increasing. Enter the DEX-EE robot. Developed by the Shadow Robot Company in collaboration with Google DeepMind, it's a three-fingered robotic hand that uses tendon-style drivers to elicit 12 degrees of freedom. Designed for "dexterous manipulation research", the team behind DEX-EE hope to demonstrate how physical interactions contribute to learning and the development of generalised intelligence.
但是，它们的先进程度正在迅速提高。DEX-EE机器人应运而生，这种三指机械手由Shadow Robot公司与谷歌DeepMind公司联合研发，采用肌腱式驱动器来产生12个自由度。DEX-EE机械手是专为“灵巧操作研究”而设计，研发团队希望证明，物理互动如何为通用人工智能的学习和发展提供帮助。
但是，它们的先进程度正在迅速提高。DEX-EE机器人应运而生，这种三指机械手由Shadow Robot公司与谷歌DeepMind公司联合研发，采用肌腱式驱动器来产生12个自由度。DEX-EE机械手是专为“灵巧操作研究”而设计，研发团队希望证明，物理互动如何为通用人工智能的学习和发展提供帮助。
Each one of its three fingers contains fingertip sensors, which provide real-time three-dimensional data on their environment, along with information regarding their position, force and inertia. The device can handle and manipulate delicate obxts including eggs and inflated balloons without damaging them. It has even learned to shake hands – something that requires it to react to interference from outside forces and unpredictable situations. At present, DEX-EE is just a research tool, not for deployment in real-world work situations where it could interact with humans.
三根手指都装有指尖传感器，可提供它们所处环境的实时三维数据，以及有关自身的位置、力量、惯性的信息。该机械手能够抓取和移动易碎的物体而不会造成损坏，例如鸡蛋、充气气球。它甚至学会了握手，这需要它对外部力量和意外状况造成的干扰做出反应。目前，DEX-EE机械手只是一种研究工具，而不是用于部署在现实世界中可与人类互动的工作场景。
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
三根手指都装有指尖传感器，可提供它们所处环境的实时三维数据，以及有关自身的位置、力量、惯性的信息。该机械手能够抓取和移动易碎的物体而不会造成损坏，例如鸡蛋、充气气球。它甚至学会了握手，这需要它对外部力量和意外状况造成的干扰做出反应。目前，DEX-EE机械手只是一种研究工具，而不是用于部署在现实世界中可与人类互动的工作场景。
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
Understanding how to perform such functions, however, will be essential as robots become increasingly present alongside people both at work and at home. How hard, for example, should a robot grip an elderly patient as they move them onto a bed?
但是了解如何执行这类功能非常重要，因为机器人越来越多地与人类一同出现在工作场所和家庭。例如：当机器人将老年患者搀扶到床上时，应该使用多大的抓取力？
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
但是了解如何执行这类功能非常重要，因为机器人越来越多地与人类一同出现在工作场所和家庭。例如：当机器人将老年患者搀扶到床上时，应该使用多大的抓取力？
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
One research project at the at the Fraunhofer IFF Institute in Madgeburg, Germany, set up a simple robot to repeatedly "punch" human volunteers in the arm a total of 19,000 times to help its algorithms learn the difference between potentially painful and comfortable forces. But some dexterous robots are already finding their way into the real world.
德国马格德堡的弗劳恩霍夫IFF研究所开展了一个研究项目，他们组装了一个简易机器人，反复“击打”人类志愿者的手臂总计19000次，从而帮助机器人算法学习可能引起疼痛感和舒适感之间的力量差异。但是一些灵巧机器人已经进入了现实世界。
德国马格德堡的弗劳恩霍夫IFF研究所开展了一个研究项目，他们组装了一个简易机器人，反复“击打”人类志愿者的手臂总计19000次，从而帮助机器人算法学习可能引起疼痛感和舒适感之间的力量差异。但是一些灵巧机器人已经进入了现实世界。
The rise of the robots
机器人的崛起
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
机器人的崛起
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
Roboticists have long dreamed of automata with anthropomorphic dexterity good enough to perform undesirable, dangerous or repetitive tasks. Rustam Stolkin, a professor of robotics at the University of Birmingham, leads a project to develop highly dexterous AI-controlled robots capable of handling nuclear waste from the energy sector, for example. While this work typically uses remotely-controlled robots, Stolkin is developing autonomous vision-guided robots that can go where it is too dangerous for humans to venture.
机器人专家一直以来的梦想是，让自动机器的仿人灵巧性足以执行人类不愿意做、具有危险性、重复性的任务。例如，伯明翰大学的机器人技术教授鲁斯塔姆·斯托尔金负责一个项目，旨在研发灵巧性高、受人工智能控制的机器人，它能够抓取能源领域的核废料。这项工作通常使用遥控机器人，但斯托尔金正在研发自主性视觉引导机器人，它们可以前往对人类来说太危险的地方去探险。
机器人专家一直以来的梦想是，让自动机器的仿人灵巧性足以执行人类不愿意做、具有危险性、重复性的任务。例如，伯明翰大学的机器人技术教授鲁斯塔姆·斯托尔金负责一个项目，旨在研发灵巧性高、受人工智能控制的机器人，它能够抓取能源领域的核废料。这项工作通常使用遥控机器人，但斯托尔金正在研发自主性视觉引导机器人，它们可以前往对人类来说太危险的地方去探险。
Perhaps the most well-known example of a real-world android is Boston Dynamics' humanoid robot Atlas, which captivated the world back in 2013 with its athletic capabilities. The most recent iteration of Atlas was unveiled in April 2024 and combines computer vision with a form of AI known as reinforcement learning, in which feedback helps AI systems to get better at what they do. According to Boston Dynamics, this allows the robot to perform complex tasks like packing or organising obxts on shelves.
现实世界中最著名的人形机器人典范可能是波士顿动力公司的Atlas，2013年它的运动技能令世界为之瞩目。最新一代Atlas于2024年4月问世，它结合了计算机视觉与强化学习人工智能技术，其反馈机制有助于人工智能系统提高它们的工作能力。据波士顿动力公司透露，这能使机器人执行复杂的任务，例如打包或整理货架上的物品。
现实世界中最著名的人形机器人典范可能是波士顿动力公司的Atlas，2013年它的运动技能令世界为之瞩目。最新一代Atlas于2024年4月问世，它结合了计算机视觉与强化学习人工智能技术，其反馈机制有助于人工智能系统提高它们的工作能力。据波士顿动力公司透露，这能使机器人执行复杂的任务，例如打包或整理货架上的物品。
But the skills required to perform many of the tasks in human-led sectors where robots such as Atlas could take off, such as manufacturing, construction and healthcare, pose a particular challenge, according to Du.
杜教授表示，Atlas这类机器人可能在制造业、建筑业、医疗保健等人类主导的领域取得成功，但它们执行各种任务所需要的技能是个严峻挑战。
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
杜教授表示，Atlas这类机器人可能在制造业、建筑业、医疗保健等人类主导的领域取得成功，但它们执行各种任务所需要的技能是个严峻挑战。
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
"This is because the majority of the hand-led motor actions in these sectors require not only precise movements but also adaptive responses to unpredictable variables such as irregular obxt shapes, varying textures, and dynamic environmental conditions," he says.
他说：“这是因为在这些领域，手部主导的大多数动运动动作不仅需要动作精确，还需要对不可预测的可变因素做出适应性反应，例如：不规则的物体形状、富于变化的纹理、动态的环境条件”。
他说：“这是因为在这些领域，手部主导的大多数动运动动作不仅需要动作精确，还需要对不可预测的可变因素做出适应性反应，例如：不规则的物体形状、富于变化的纹理、动态的环境条件”。
Du and his colleagues are working on highly-dexterous construction robots that use embodied AI to learn motor skills by interacting with the real world.
杜教授和他的同事正在研发高度灵巧的建筑机器人，它采用具身智能技术，通过与现实世界进行互动来学习运动技巧。
杜教授和他的同事正在研发高度灵巧的建筑机器人，它采用具身智能技术，通过与现实世界进行互动来学习运动技巧。
At present, most robots are trained on specific tasks, one at a time, which means they struggle to adapt to new or unpredictable situations. This limits their applications. But Du argues that this is changing. "Recent advancements suggest that robots could eventually learn adaptable, versatile skills that enable them to handle a variety of tasks without prior specific training," he says.
目前，大多数机器人都会接受特定任务的训练（逐个进行），这意味着他们很难适应新的或不可预测的情况，这限制了它们的用途。但杜教授认为，情况正在发生变化。他说：“最新的研究进展表明，机器人最终可能学习适应性的通用技能，使他们不必事先经过专项训练，就能胜任各种任务”。
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
目前，大多数机器人都会接受特定任务的训练（逐个进行），这意味着他们很难适应新的或不可预测的情况，这限制了它们的用途。但杜教授认为，情况正在发生变化。他说：“最新的研究进展表明，机器人最终可能学习适应性的通用技能，使他们不必事先经过专项训练，就能胜任各种任务”。
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
Tesla also gave its own humanoid robot Optimus a new hand at the end of 2024. The company released a video of the bot catching a tennis ball in mid-air. However, it was tele-operated by remote manual control, rather than autonomous, according to the engineers behind it. The hand has 25 degrees of freedom, they claim.
2024年底，特斯拉也给自家的人形机器人擎天柱（Optimus）安装了一只新型机械手，并发布了一段它在半空中接住网球的视频。然而，负责研发的工程师指出，该机械手是由手动遥控器进行遥操控的，而不是自动运行的。他们声称该机械手有25个自由度。
2024年底，特斯拉也给自家的人形机器人擎天柱（Optimus）安装了一只新型机械手，并发布了一段它在半空中接住网球的视频。然而，负责研发的工程师指出，该机械手是由手动遥控器进行遥操控的，而不是自动运行的。他们声称该机械手有25个自由度。
But while some innovators have sought to recreate human hands and arms in machine form, others have opted for very different approaches to dexterity. Cambridge based robotics company Dogtooth Technologies has created soft fruit-picking robots, with highly dexterous arms and precision pincers capable of picking and packing delicate fruits like strawberries and raspberries at the same speed as human workers.
有些创新者试图以机械的形式再造人手和手臂，但也有创新者采取了截然不同的方式来实现灵巧性。总部位于英国剑桥的机器人公司Dogtooth Technologies制造出软果采摘机器人，它拥有高度灵巧的手臂和精密的钳子，能够以人工同样的速度采摘和包装草莓、覆盆子等娇嫩的水果。
有些创新者试图以机械的形式再造人手和手臂，但也有创新者采取了截然不同的方式来实现灵巧性。总部位于英国剑桥的机器人公司Dogtooth Technologies制造出软果采摘机器人，它拥有高度灵巧的手臂和精密的钳子，能够以人工同样的速度采摘和包装草莓、覆盆子等娇嫩的水果。
The idea for the fruit-picking robots came to co-founder and chief executive Duncan Robertson while he was lying on a beach in Morocco. With a background in machine learning and computer vision, Robertson wanted to apply his skills to help clean up the litter on the beach, by creating a low-cost robot which could identify, sort, and remove detritus. When he returned home, he applied the same logic to soft fruit farming.
水果采摘机器人是该公司的联合创始人、首席执行官邓肯·罗伯逊躺在摩洛哥的海滩上时想出来的。罗伯逊拥有机器学习和计算机视觉方面的知识背景，他希望运用自己的技术来帮忙清理海滩上的垃圾，于是发明了一种可以识别、分拣、清理垃圾的低成本机器人。他回家后将同样的逻辑应用于软果种植领域。
水果采摘机器人是该公司的联合创始人、首席执行官邓肯·罗伯逊躺在摩洛哥的海滩上时想出来的。罗伯逊拥有机器学习和计算机视觉方面的知识背景，他希望运用自己的技术来帮忙清理海滩上的垃圾，于是发明了一种可以识别、分拣、清理垃圾的低成本机器人。他回家后将同样的逻辑应用于软果种植领域。
The robots he developed along with the team at Dogtooth use machine learning models to deploy some of the skills that we as humans possess instinctively. Each of the robot's two arms has two colour cameras, much like eyes, which allow them to identify the ripeness of the berries and determine the depth of each of the target fruits from its end "effector", or gripping device.
他与Dogtooth公司的团队共同研发的机器人，利用机器学习模型来施展我们人类与生俱来的部分技能。机器人的双臂各有两个彩色摄像头，像眼睛一样识别浆果的成熟度，测定每只目标水果与末端“执行器”（即抓取装置）之间的距离。
他与Dogtooth公司的团队共同研发的机器人，利用机器学习模型来施展我们人类与生俱来的部分技能。机器人的双臂各有两个彩色摄像头，像眼睛一样识别浆果的成熟度，测定每只目标水果与末端“执行器”（即抓取装置）之间的距离。
The robots map the dispersal and arrangement of ripe fruits on a plant and turn this into a sequence of actions, with precise route planning necessary in order to guide the picker arm to the fruit's stem in order to make a cut.
机器人绘制出成熟水果在植株上的分布和排列图，并将其转化为一系列动作，精确的路线规划是必要的，以便引导采摘手臂对准果柄进行切割。
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
机器人绘制出成熟水果在植株上的分布和排列图，并将其转化为一系列动作，精确的路线规划是必要的，以便引导采摘手臂对准果柄进行切割。
原创翻译：龙腾网 https://www.ltaaa.cn 转载请注明出处
Dogooth's robot's arms each have seven degrees of freedom, the same as the human arm, meaning these appendages can manoeuvre well enough to find the optimal angle for reaching each berry without damaging others still on the plant. The grasping device then gently grips the fruit by the stem, passing it into an inspection chamber before carefully placing the berry in a punnet for distribution. Another strawberry-picking system, created by Octinion, uses soft grippers to grasp the fruit as it transfers it from plant to basket.
Dogtooth机器人的手臂就像人类手臂一样各有七个自由度，这意味着这些机械臂可以灵活自如地调整到摘取每颗浆果的最佳角度，且不会损伤植株上其余的果实。随后，抓取装置会轻轻地握住果柄，把浆果送入检测室，然后小心翼翼地把浆果放入果篮以便进行配送。还有一种由Octinion公司研发的草莓采摘系统，它利用柔性抓取器采摘水果并放入果篮中。
Dogtooth机器人的手臂就像人类手臂一样各有七个自由度，这意味着这些机械臂可以灵活自如地调整到摘取每颗浆果的最佳角度，且不会损伤植株上其余的果实。随后，抓取装置会轻轻地握住果柄，把浆果送入检测室，然后小心翼翼地把浆果放入果篮以便进行配送。还有一种由Octinion公司研发的草莓采摘系统，它利用柔性抓取器采摘水果并放入果篮中。
评论翻译
网友评论
@DavidStruveDesigns
The pressure feedback system is a real game-changer. Able-bodied people with all their limbs don't tend to realise how amazing it is that we can use our hands whilst hardly ever looking at them, and yet get the perfect level of grip on an obxt pretty much every time. When you're suddenly made aware of it, like watching a video such as this one, it makes you realise just how complex and amazing the human body is.
压力反馈系统是一项真正的变革性技术。四肢健全的人往往意识不到，我们使用双手时几乎从来不会注视它们，但几乎每次都能恰到好处地握住物体，这是多么神奇的事情。当你突然意识到这一点时，比如通过观看这样的视频，你就会明白人体是多么复杂多么神奇了。
The pressure feedback system is a real game-changer. Able-bodied people with all their limbs don't tend to realise how amazing it is that we can use our hands whilst hardly ever looking at them, and yet get the perfect level of grip on an obxt pretty much every time. When you're suddenly made aware of it, like watching a video such as this one, it makes you realise just how complex and amazing the human body is.
压力反馈系统是一项真正的变革性技术。四肢健全的人往往意识不到，我们使用双手时几乎从来不会注视它们，但几乎每次都能恰到好处地握住物体，这是多么神奇的事情。当你突然意识到这一点时，比如通过观看这样的视频，你就会明白人体是多么复杂多么神奇了。
and how much of our bodily actions/functions are almost completely automated, without need for concious processing, focus or thought. Also makes you wonder, just how much of me is actually me in control, and how much is my body just a pre-programmed robot that I'm merely occupying and taking a ride in.
我们身体的很多动作和功能几乎完全是自动进行的，无需下意识地处理、专注、思考。这也会让你不禁思考，自己在多大程度上真正是由自己控制的，我的身体在多大程度上只是一台预编程的机器人，而我不过是在使用和乘坐这台机器人而已。
我们身体的很多动作和功能几乎完全是自动进行的，无需下意识地处理、专注、思考。这也会让你不禁思考，自己在多大程度上真正是由自己控制的，我的身体在多大程度上只是一台预编程的机器人，而我不过是在使用和乘坐这台机器人而已。
@lumberjackofalltrades
I'm having a hard time believing that we're so close to actual functioning Star Wars technology. What a time to be alive!
我简直不敢相信，我们距离实现《星球大战》里的技术这么近了，活在这个时代，真是太棒了！
I'm having a hard time believing that we're so close to actual functioning Star Wars technology. What a time to be alive!
我简直不敢相信，我们距离实现《星球大战》里的技术这么近了，活在这个时代，真是太棒了！
@Kotmazay
Yes, muscul sensors are from 70-s - real star wars tehnology lol
是的，肌肉传感器是上世纪70年代的产物——这可是真正的《星球大战》式技术，哈哈。
Yes, muscul sensors are from 70-s - real star wars tehnology lol
是的，肌肉传感器是上世纪70年代的产物——这可是真正的《星球大战》式技术，哈哈。
@sheepasus
It will still take a while, the bionic legs are really close to being as good as normal legs, at least for most daily living tasks, but hands are such a biological marvel, they're really difficult to replace a normal hand, as they're just not space efficient. Most bionic hands have either motors in the socket, or in the hand, or even both, and even then, we can only fulfill a partial functionality, because we do not have enough space for the additional motors needed for a fully functional hand. In fact, there is still an over 40% rejection rate to bionic hand prosthetics.
还有一定的差距。仿生腿至少在大多数日常任务中几乎可以媲美人腿了，但人手真的是一大生物奇迹，仿生手很难代替人手，因为空间利用率不够。大多数仿生手的电机要么安装在接受腔，要么安装在手部，也有两处都安装的。但即便如此，我们也只能实现部分功能，因为我们没有足够空间为功能完备的仿生手安装更多所需的电机。事实上，仿生假肢的弃用率仍超过40%。
It will still take a while, the bionic legs are really close to being as good as normal legs, at least for most daily living tasks, but hands are such a biological marvel, they're really difficult to replace a normal hand, as they're just not space efficient. Most bionic hands have either motors in the socket, or in the hand, or even both, and even then, we can only fulfill a partial functionality, because we do not have enough space for the additional motors needed for a fully functional hand. In fact, there is still an over 40% rejection rate to bionic hand prosthetics.
还有一定的差距。仿生腿至少在大多数日常任务中几乎可以媲美人腿了，但人手真的是一大生物奇迹，仿生手很难代替人手，因为空间利用率不够。大多数仿生手的电机要么安装在接受腔，要么安装在手部，也有两处都安装的。但即便如此，我们也只能实现部分功能，因为我们没有足够空间为功能完备的仿生手安装更多所需的电机。事实上，仿生假肢的弃用率仍超过40%。
@PBST_RAIDZ
It's actually a step ahead as in star wars you can't feel stuff with your prospectic hand or arm.
这其实是一大进步，因为在《星球大战》中，你无法用假手或假肢感知物体。
It's actually a step ahead as in star wars you can't feel stuff with your prospectic hand or arm.
这其实是一大进步，因为在《星球大战》中，你无法用假手或假肢感知物体。
@erikmckoul2478
Next they need to figure out how to attach them to a robotic arm for people who can't lift their arms, so I can eat chips without help for once.
接下来，他们需要研究如何将仿生手安装到机械臂上，供那些无法抬起手臂的人使用，这样我就终于能不用别人帮忙自己吃薯片了。
Next they need to figure out how to attach them to a robotic arm for people who can't lift their arms, so I can eat chips without help for once.
接下来，他们需要研究如何将仿生手安装到机械臂上，供那些无法抬起手臂的人使用，这样我就终于能不用别人帮忙自己吃薯片了。
@radamanthys0223
it's indeed been moving at a faster pace in the last 10 years or so, neural interfaces and direct to bone fitting are the next steps, this company that makes the BIOM foot is/was working on such neural interfaces though I haven't heard much from them in the last 5 years or so. Mechanically we are already able to produce prosthesis with close to natural degrees of freedom (cue the HK university ankle desgin that can tiptoe). next 10 years on the tech seem promising
在过去十年左右的时间里，假肢技术的发展速度确实加快了。接下来的发展方向是神经接口和骨整合技术。制造BIOM仿生腿的这家公司之前在研发这类神经接口，但大约五年时间过去了，我没听说他们取得了多大进展。从机械技术的角度，我们已经能够制造自由度接近自然肢体的假肢了（例如：中国香港（特区）大学设计的能够踮脚的踝关节）。看来未来十年，这项技术前景广阔。
it's indeed been moving at a faster pace in the last 10 years or so, neural interfaces and direct to bone fitting are the next steps, this company that makes the BIOM foot is/was working on such neural interfaces though I haven't heard much from them in the last 5 years or so. Mechanically we are already able to produce prosthesis with close to natural degrees of freedom (cue the HK university ankle desgin that can tiptoe). next 10 years on the tech seem promising
在过去十年左右的时间里，假肢技术的发展速度确实加快了。接下来的发展方向是神经接口和骨整合技术。制造BIOM仿生腿的这家公司之前在研发这类神经接口，但大约五年时间过去了，我没听说他们取得了多大进展。从机械技术的角度，我们已经能够制造自由度接近自然肢体的假肢了（例如：中国香港（特区）大学设计的能够踮脚的踝关节）。看来未来十年，这项技术前景广阔。
@Rizzob17
It makes me think of Terminator. Especially with AI tech accelerating at a much faster rate. Think of those evil enough to pass along their biases to AI, put it in a full cyborg with immense strength, speed and skill.
这让我想起了《终结者》。尤其是在人工智能技术极大加快发展步伐的当下。想想那些恶人把自己的偏见灌输给人工智能，再把这样的人工智能应用于发展成熟的赛博格（半机器人），它们拥有超强的力量、速度、技能。
It makes me think of Terminator. Especially with AI tech accelerating at a much faster rate. Think of those evil enough to pass along their biases to AI, put it in a full cyborg with immense strength, speed and skill.
这让我想起了《终结者》。尤其是在人工智能技术极大加快发展步伐的当下。想想那些恶人把自己的偏见灌输给人工智能，再把这样的人工智能应用于发展成熟的赛博格（半机器人），它们拥有超强的力量、速度、技能。
@therealgoogas8700
In at most like 10 years if the way things are going don’t get better we gonna be plunged into a mini dark age for a while more and more people can’t afford to buy a home and with crop failures world wide food shortages will become common place
照目前的情况，如果在最多10年左右的时间里得不到改善，我们将会陷入短暂的“小黑暗时代”。届时越来越多的人将买不起房，由于全球农作物歉收，粮食短缺将成为普遍现象。
In at most like 10 years if the way things are going don’t get better we gonna be plunged into a mini dark age for a while more and more people can’t afford to buy a home and with crop failures world wide food shortages will become common place
照目前的情况，如果在最多10年左右的时间里得不到改善，我们将会陷入短暂的“小黑暗时代”。届时越来越多的人将买不起房，由于全球农作物歉收，粮食短缺将成为普遍现象。
@Optimumlabsllc
I make sockets and I can tell you, sockets they won’t go obsolete. Right now bone integration have a failure rate that can cause you to become even more of an amputee. Not to mention there will always be people who don’t want a rod sticking out of their body permanently. I had a patient that fell on his once. Splintered what was left of his bone. Now, As the bone integration get better, these problems should subside but sockets won’t be obsolete. Especially with people like me, innovating to make sure every patient has the most comfortable experience with my prosthetics.
我制造假肢接受腔，我可以告诉你，假肢接受腔不会被淘汰。目前，骨整合技术存在一定的失败率，这可能导致截肢患者雪上加霜，更何况始终有人不希望自己的身体永久性突出一根棍子。我有个患者在使用骨整合假肢时摔倒了，导致残留的骨头碎裂。如今随着骨整合技术的进步，这些问题应该会有所缓解，但假肢接受腔不会被淘汰。尤其是有我这样的人，通过不断创新来确保每位患者在使用我制造的假肢时，都能获得最舒适的体验。
I make sockets and I can tell you, sockets they won’t go obsolete. Right now bone integration have a failure rate that can cause you to become even more of an amputee. Not to mention there will always be people who don’t want a rod sticking out of their body permanently. I had a patient that fell on his once. Splintered what was left of his bone. Now, As the bone integration get better, these problems should subside but sockets won’t be obsolete. Especially with people like me, innovating to make sure every patient has the most comfortable experience with my prosthetics.
我制造假肢接受腔，我可以告诉你，假肢接受腔不会被淘汰。目前，骨整合技术存在一定的失败率，这可能导致截肢患者雪上加霜，更何况始终有人不希望自己的身体永久性突出一根棍子。我有个患者在使用骨整合假肢时摔倒了，导致残留的骨头碎裂。如今随着骨整合技术的进步，这些问题应该会有所缓解，但假肢接受腔不会被淘汰。尤其是有我这样的人，通过不断创新来确保每位患者在使用我制造的假肢时，都能获得最舒适的体验。
@Derpachu
Amazing advancements. I’m curious if it’s possible to automate the twisting of the joints. It might take some innovation but after that we pretty much got fully functional hands. Would need some more programming to make the fingers swivel but after that we have hands that could do everything natural hands can do and possibly better. Attachment to bones and nervous system would probably be the next step
这是惊人的进步。我好奇我们能否实现关节的自动扭转。这可能需要一些创新，但只要做到这一点，我们基本上就有功能完备的仿生手了。我们需要更多的编程才能实现手指的扭转，但只要做到这一点，仿生手就能做到人手所能做的一切事情，甚至可能更加出色。下一个目标可能是仿生手连接骨骼和神经系统。
Amazing advancements. I’m curious if it’s possible to automate the twisting of the joints. It might take some innovation but after that we pretty much got fully functional hands. Would need some more programming to make the fingers swivel but after that we have hands that could do everything natural hands can do and possibly better. Attachment to bones and nervous system would probably be the next step
这是惊人的进步。我好奇我们能否实现关节的自动扭转。这可能需要一些创新，但只要做到这一点，我们基本上就有功能完备的仿生手了。我们需要更多的编程才能实现手指的扭转，但只要做到这一点，仿生手就能做到人手所能做的一切事情，甚至可能更加出色。下一个目标可能是仿生手连接骨骼和神经系统。
很赞 3
收藏