<p>在香港中文大学（CUHK）举行的 ATEC2025 真实世界极限挑战赛中，参赛机器人面临着严峻的考验：泥泞、楼梯、摇晃的桥梁和无结构的户外环境。与通常在室内进行的机器人比赛不同，这场比赛故意将智能机器人置于真实世界的不可预测条件中——组织者表示，这一举措对于弥合实验室演示与实际部署之间的差距至关重要。</p>
<p>ATEC2025 的共同主席、香港工程学院院士刘云辉教授将此次活动视为必要的压力测试。他指出：“今年的比赛旨在回答一个根本性的问题：机器人真的能离开实验室并适应我们不可预测的世界吗？”</p>
<p><img src="https://imageproxy.pbkrs.com/https://i0.wp.com/technode.com/wp-content/uploads/2025/12/atec-2025.jpg/query-cmVzaXplPTc4MCwxMTcwJnNzbD0x?x-oss-process=image/auto-orient,1/interlace,1/resize,w_1440,h_1440/quality,q_95/format,jpg" alt="" original-src="https://imageproxy.pbkrs.com/https://i0.wp.com/technode.com/wp-content/uploads/2025/12/atec-2025.jpg/query-cmVzaXplPTc4MCwxMTcwJnNzbD0x"/></p>
<p>ATEC2025 背后的愿景反映了人工智能的更广泛转变——这一点得到了创始成员蚂蚁集团的呼应。蚂蚁集团对 ATEC2025 的支持源于一个核心信念，即人工通用智能的未来在于机器智能与物理世界的深度融合。</p>
<p><strong>三项核心能力的测试</strong></p>
<p>在来自全球大学和行业的 392 支参赛队伍中，只有 13 支晋级为期两天的决赛：真实世界极限挑战赛。他们的任务是完成四项真实世界挑战：垃圾分类、自动浇水、野外定向和过桥。</p>
<p>这些任务旨在评估刘教授所称的 “机器人三项核心能力”：运动、操作和环境改造。</p>
<p>“我们强调运动与操作的结合，” 刘在媒体采访中解释道。“之前，许多机器人比赛主要集中在行走上——甚至是马拉松。但在这里，机器人还必须抓取物体、倒水和改变环境以完成任务。”</p>
<p><strong>通过失败取得进展</strong></p>
<p>困难显而易见。许多队伍面临挑战，甚至基本的抓取也需要多次尝试。“一些最优秀的队伍需要 10 次或 20 次尝试才能成功，” 刘指出。</p>
<p>然而，这种不完整的表现是在首次真实世界格式中所预期的。“这是我们第一次做这样的事情。失败是正常的，” 刘说。“重要的是我们看到进展——一些队伍在反复尝试后确实完成了任务。”</p>
<p><img src="https://imageproxy.pbkrs.com/https://i0.wp.com/technode.com/wp-content/uploads/2025/12/atec-2025-robot.jpg/query-cmVzaXplPTc4MCw1NTcmc3NsPTE?x-oss-process=image/auto-orient,1/interlace,1/resize,w_1440,h_1440/quality,q_95/format,jpg" alt="" original-src="https://imageproxy.pbkrs.com/https://i0.wp.com/technode.com/wp-content/uploads/2025/12/atec-2025-robot.jpg/query-cmVzaXplPTc4MCw1NTcmc3NsPTE"/></p>
<p>刘强调，ATEC2025 并不是关于精美的演示，而是关于真实世界的稳健性。“你在网上看到的机器人视频通常是经过编辑的亮点，经过数十次失败的尝试，” 他说。“在这里，我们看到的是原始过程。在平坦的地面上行走可能看起来可靠，但在不平坦的地形或狭窄的楼梯上，失败率显著上升。”</p>
<p><strong>展望未来</strong></p>
<p>虽然获胜队伍将获得 15 万美元的奖金，但刘明确表示，ATEC 的主要目标不是商业化，而是基础性进步。“我们希望这能激励年轻人加入这个领域，并推动社区共同解决难题，” 他说。尽管与投资者的合作可能会在后期出现，“但这场比赛根本上是关于测试机器人智能。”</p>
<p>展望未来，刘认为有意义的真实世界部署仍需数年时间。“如今的机器人处理简单的服务，如送餐，但在家庭环境中进行烹饪或洗衣等任务需要更高的可靠性、安全性和灵活性，” 他警告道。“这不会在两三年内实现——甚至可能在五年内也不会。”</p>
<p>“目标，” 刘说，“是让机器人可靠地完成 20% 到 30% 的基本人类任务，如垃圾分类或浇水，成功率达到 90%。仅此一项就将是变革性的。”</p>
<p>尽管如此，他仍然将 ATEC2025 视为一个关键步骤。通过将评估锚定在人类相关能力上——不仅在准确性上衡量表现，还在功能等效于人类行为上进行评估——这场比赛旨在探索该领域的新基准。</p>
<p>在学术界、工业界和公共部门的强大支持下，并利用大湾区的硬件和人才生态系统，ATEC 可能成为一个反复出现的试验场，在这里，具身人工智能的未来将在土壤、风和雨中锻造，而不是在模拟中。</p>

蚂蚁集团

<p>ATEC2025 在香港中文大学举行的真实世界极限挑战测试了机器人在真实环境中的表现，强调了运动、操作和环境改造。该活动得到了蚂蚁集团的支持，旨在缩小实验室演示与实际应用之间的差距。尽管面临挑战，进展依然显著，突显了真实世界的稳健性比精致演示更为重要。比赛旨在激励机器人智能的进步，未来的应用预计需要数年时间。ATEC2025 是探索具身人工智能新基准的重要一步</p>

<p>At the ATEC2025 Real-World Extreme Challenge, held at The Chinese University of Hong Kong (CUHK), competing robots faced a grueling test: mud, stairs, swaying bridges, and unstructured outdoor environments. Unlike typical robotics contests staged indoors, this competition deliberately placed intelligent robots in the unpredictable conditions of the real world—a move organizers say is essential to bridge the gap between laboratory demonstrations and actual deployment.</p>
<div class="lb-trans"><p>在香港中文大学（CUHK）举行的 ATEC2025 真实世界极限挑战赛中，参赛机器人面临着严峻的考验：泥泞、楼梯、摇晃的桥梁和无结构的户外环境。与通常在室内进行的机器人比赛不同，这场比赛故意将智能机器人置于真实世界的不可预测条件中——组织者表示，这一举措对于弥合实验室演示与实际部署之间的差距至关重要。</p>
</div><p>Professor Yunhui Liu, Co-Chair of ATEC2025 and Fellow of the Hong Kong Academy of Engineering, framed the event as a necessary stress test. As he noted, “This year’s competition sought to answer a fundamental question: Can robots truly leave the lab and adapt to our unpredictable world?”</p>
<div class="lb-trans"><p>ATEC2025 的共同主席、香港工程学院院士刘云辉教授将此次活动视为必要的压力测试。他指出：“今年的比赛旨在回答一个根本性的问题：机器人真的能离开实验室并适应我们不可预测的世界吗？”</p>
</div><p><img src="https://imageproxy.pbkrs.com/https://i0.wp.com/technode.com/wp-content/uploads/2025/12/atec-2025.jpg/query-cmVzaXplPTc4MCwxMTcwJnNzbD0x" alt="" original-src="https://i0.wp.com/technode.com/wp-content/uploads/2025/12/atec-2025.jpg?resize=780%2C1170&amp;ssl=1"/></p>
<p>The vision behind ATEC2025 reflects a broader shift in artificial intelligence—one echoed by founding member Ant Group. Ant Group’s support for ATEC2025 is rooted in a core belief that the future of artificial general intelligence lies in the deep integration of machine intelligence with the physical world.</p>
<div class="lb-trans"><p>ATEC2025 背后的愿景反映了人工智能的更广泛转变——这一点得到了创始成员蚂蚁集团的呼应。蚂蚁集团对 ATEC2025 的支持源于一个核心信念，即人工通用智能的未来在于机器智能与物理世界的深度融合。</p>
</div><p><strong>A Test of Three Core Capabilities</strong></p>
<div class="lb-trans"><p><strong>三项核心能力的测试</strong></p>
</div><p>Out of 392 teams from universities and industries worldwide that participated in the online qualifiers, only 13 advanced to the two-day final: the Real-World Extreme Challenge. They were tasked with completing four real-world challenges: waste sorting, autonomous plant watering, field orienteering, and bridge crossing.</p>
<div class="lb-trans"><p>在来自全球大学和行业的 392 支参赛队伍中，只有 13 支晋级为期两天的决赛：真实世界极限挑战赛。他们的任务是完成四项真实世界挑战：垃圾分类、自动浇水、野外定向和过桥。</p>
</div><p>These tasks were designed to evaluate what Prof. Liu calls the “Three Core Capabilities of Robotics”: locomotion, manipulation, and environmental modification.</p>
<div class="lb-trans"><p>这些任务旨在评估刘教授所称的 “机器人三项核心能力”：运动、操作和环境改造。</p>
</div><p>“We emphasize combining movement and operation,” Liu explained in media interviews. “Previously, many robot competitions focused mainly on walking—even marathons. But here, robots must also grasp objects, pour water, and change their environment to complete tasks.”</p>
<div class="lb-trans"><p>“我们强调运动与操作的结合，” 刘在媒体采访中解释道。“之前，许多机器人比赛主要集中在行走上——甚至是马拉松。但在这里，机器人还必须抓取物体、倒水和改变环境以完成任务。”</p>
</div><p><strong>Progress Through Failure</strong></p>
<div class="lb-trans"><p><strong>通过失败取得进展</strong></p>
</div><p>The difficulty was evident. Many teams struggled, with even basic grasping requiring numerous attempts. “Some of the best teams needed 10 or 20 tries to succeed,” Liu noted.</p>
<div class="lb-trans"><p>困难显而易见。许多队伍面临挑战，甚至基本的抓取也需要多次尝试。“一些最优秀的队伍需要 10 次或 20 次尝试才能成功，” 刘指出。</p>
</div><p>However, such incomplete performances were expected in this inaugural real-world format. “This is the first time we’ve done something like this. Failure is normal,” Liu said. “What matters is that we see progress—some teams did fully complete the tasks after repeated trials.”</p>
<div class="lb-trans"><p>然而，这种不完整的表现是在首次真实世界格式中所预期的。“这是我们第一次做这样的事情。失败是正常的，” 刘说。“重要的是我们看到进展——一些队伍在反复尝试后确实完成了任务。”</p>
</div><p><img src="https://imageproxy.pbkrs.com/https://i0.wp.com/technode.com/wp-content/uploads/2025/12/atec-2025-robot.jpg/query-cmVzaXplPTc4MCw1NTcmc3NsPTE" alt="" original-src="https://i0.wp.com/technode.com/wp-content/uploads/2025/12/atec-2025-robot.jpg?resize=780%2C557&amp;ssl=1"/></p>
<p>Liu emphasized that ATEC2025 is not about polished demos but real-world robustness. “Videos of robots you see online are often edited highlights after dozens of failed attempts,” he said. “Here, we see the raw process. Walking on flat ground may look reliable, but on uneven terrain or narrow stairs, failure rates rise significantly.”</p>
<div class="lb-trans"><p>刘强调，ATEC2025 并不是关于精美的演示，而是关于真实世界的稳健性。“你在网上看到的机器人视频通常是经过编辑的亮点，经过数十次失败的尝试，” 他说。“在这里，我们看到的是原始过程。在平坦的地面上行走可能看起来可靠，但在不平坦的地形或狭窄的楼梯上，失败率显著上升。”</p>
</div><p><strong>Looking to the Future</strong></p>
<div class="lb-trans"><p><strong>展望未来</strong></p>
</div><p>While the winning team will receive a $150,000 prize, Liu made clear that ATEC’s primary aim is not commercialization but foundational advancement. “We hope this inspires young people to join the field and pushes the community to solve hard problems together,” he said. Though partnerships with investors could emerge later, “this competition is fundamentally about testing robotic intelligence.”</p>
<div class="lb-trans"><p>虽然获胜队伍将获得 15 万美元的奖金，但刘明确表示，ATEC 的主要目标不是商业化，而是基础性进步。“我们希望这能激励年轻人加入这个领域，并推动社区共同解决难题，” 他说。尽管与投资者的合作可能会在后期出现，“但这场比赛根本上是关于测试机器人智能。”</p>
</div><p>Looking ahead, Liu believes meaningful real-world deployment remains years away. “Robots today handle simple services like food delivery, but tasks like cooking or laundry in a home setting require far greater reliability, safety, and dexterity,” he cautioned. “It won’t happen in two or three years—maybe not even in five.”</p>
<div class="lb-trans"><p>展望未来，刘认为有意义的真实世界部署仍需数年时间。“如今的机器人处理简单的服务，如送餐，但在家庭环境中进行烹饪或洗衣等任务需要更高的可靠性、安全性和灵活性，” 他警告道。“这不会在两三年内实现——甚至可能在五年内也不会。”</p>
</div><p>“The goal,” Liu said, “is for robots to reliably perform even 20–30% of basic human tasks, like sorting trash or watering plants, with 90% success. That alone would be transformative.”</p>
<div class="lb-trans"><p>“目标，” 刘说，“是让机器人可靠地完成 20% 到 30% 的基本人类任务，如垃圾分类或浇水，成功率达到 90%。仅此一项就将是变革性的。”</p>
</div><p>Still, he sees ATEC2025 as a critical step. By anchoring evaluation in human-relevant capabilities—measuring performance not just in accuracy but in functional equivalence to human actions—the competition aims to explore new benchmarks for the field.</p>
<div class="lb-trans"><p>尽管如此，他仍然将 ATEC2025 视为一个关键步骤。通过将评估锚定在人类相关能力上——不仅在准确性上衡量表现，还在功能等效于人类行为上进行评估——这场比赛旨在探索该领域的新基准。</p>
</div><p>With strong support from academia, industry, and the public sector, and leveraging the hardware and talent ecosystem of the Greater Bay Area, ATEC may well become a recurring proving ground where the future of embodied AI is forged—not in simulation, but in soil, wind, and rain.</p>
<div class="lb-trans"><p>在学术界、工业界和公共部门的强大支持下，并利用大湾区的硬件和人才生态系统，ATEC 可能成为一个反复出现的试验场，在这里，具身人工智能的未来将在土壤、风和雨中锻造，而不是在模拟中。</p>
</div>

ATEC2025 标志着现实世界机器人技术的一次重大飞跃——每一次绊倒都推动着进步