Examining how robots are moving from demonstrations to daily use.
Updated
January 8, 2026 6:22 PM
An industrial robotic arm capable of autonomous welding. PHOTO: ADOBE STOCK
CES 2026 did not frame robotics as a distant future or a technological spectacle. Instead, it highlighted machines designed for the slow, practical work of fitting into human systems. Across the show floor, robots were no longer performing for attention but being shaped by real-world constraints—space, safety, fatigue and repetition.
They appeared in factories, homes, emergency settings and industrial sites, each responding to a specific kind of human limitation. Together, these four robots reveal how robotics is being redefined: not as a replacement for people, but as infrastructure that quietly takes on work humans are least meant to carry alone.
Hyundai Motor unveiled its electric humanoid robot, Atlas, during a media day on January 5, 2026, at the Mandalay Bay Convention Center in Las Vegas as part of CES 2026. Developed with Boston Dynamics, Hyundai’s U.S.-based robotics subsidiary, Atlas was presented in two forms: a research prototype and a commercial model designed for real factory environments.
Shown under the theme “AI Robotics, Beyond the Lab to Life: Partnering Human Progress,” Atlas is designed to work alongside humans rather than replace them. The premise is straightforward—robots take on physically demanding and repetitive tasks such as sorting and assembly, while people focus on work requiring judgment, creativity and decision-making.
Built for industrial use, the commercial version of Atlas is designed to adapt quickly, with Hyundai stating it can learn new tasks within a day. Its adult-sized humanoid form features 56 degrees of freedom, enabling flexible, human-like movement. Tactile sensors in its hands and a 360-degree vision system support spatial awareness and precise operation.
Atlas is also engineered for demanding conditions. It can lift up to 50 kilograms, operate in temperatures ranging from –20°C to 40°C and is waterproof, making it suitable for challenging factory settings.
Looking ahead, Hyundai expects Atlas to begin with parts sorting and sequencing by 2028, move into assembly by 2030 and later take on precision tasks that require sustained physical effort and focus.
Widemount’s Smart Firefighting Robot is designed to operate in environments that are difficult and dangerous for humans to enter. Developed by Widemount Dynamics, a spinout from the Hong Kong Polytechnic University, the robot is built to support emergency teams during fires, particularly in enclosed and smoke-filled spaces.
The robot can move through buildings and industrial facilities even when visibility is near zero. Rather than relying on cameras or GPS, it uses radar-based mapping to understand its surroundings and determine a safe path forward. This allows it to continue operating when smoke, heat or debris would normally restrict access.
As it approaches a fire, the robot analyses the burning object. Its onboard AI helps identify the material involved and selects an appropriate extinguishing method. Sensors simultaneously assess flame intensity and send real-time updates to command centres, giving responders clearer situational awareness.
When actively fighting a fire, the robot can aim directly at the source and deploy extinguishing agents autonomously. The system continuously adjusts its actions based on incoming sensor data, reducing the need for constant human intervention during high-risk situations.
At CES 2026, LG Electronics offered a glimpse into how household work could gradually shift from people to machines. The company introduced LG CLOiD, an AI-powered home robot designed to manage everyday chores by working directly with connected appliances within LG’s ThinQ ecosystem.
Designed for indoor living spaces, CLOiD features a compact upper body with two articulated arms, a head unit and a wheeled base that enables steady movement across floors. Its torso can tilt to adjust height, allowing it to reach items placed low or on kitchen counters. The arms and hands are built for careful handling, enabling the robot to grip common household objects rather than heavy tools. The head also functions as a mobile control unit, housing cameras, sensors, a display and voice interaction capabilities for communication and monitoring.
In practice, CLOiD acts as a task coordinator. It can retrieve items from appliances, operate ovens and washing machines and manage laundry cycles from start to finish, including folding and stacking clothes. By connecting multiple devices through the ThinQ system, the robot turns separate appliances into a single, coordinated workflow.
These capabilities are supported by LG’s Physical AI system. CLOiD uses vision to recognise objects and interpret its surroundings, language processing to understand instructions and action control to execute tasks step by step. Together, these systems allow the robot to follow routines, respond to user input and adjust task execution over time.
Doosan Robotics introduced Scan & Go at CES 2026, an AI-driven robotic system designed to automate large-scale surface repair and inspection. The solution targets environments with complex, irregular surfaces that are difficult to pre-program, such as aircraft structures, wind turbine blades and large industrial installations.
Scan & Go operates by scanning surfaces on site and building an understanding of their shape in real time. Instead of relying on detailed digital models or manual coding, the system plans its movements based on live data. This enables it to adapt to variations in size, curvature and surface condition without extensive setup.
The underlying technology combines 3D sensing with AI-based motion planning. The system interprets surface data, generates tool paths and refines its actions as work progresses. In practical terms, this reduces manual intervention while maintaining consistency across large work areas.
By handling surface preparation and inspection tasks that are time-consuming and physically demanding, Scan & Go is positioned as a support tool for industrial teams operating at scale.
Taken together, these robots signal a clear shift in how machines are being designed and deployed. Across factories, homes, emergency sites and industrial infrastructure, robotics is moving beyond demonstrations and into practical roles that support human work.
The unifying theme is not replacement, but relief—robots taking on tasks that are repetitive, hazardous or physically demanding. CES 2026 suggests that robotics is evolving from spectacle to utility, with a growing focus on systems that adapt to real environments, respond to genuine constraints and integrate into everyday workflows.
Keep Reading
A closer look at how machine intelligence is helping doctors see cancer in an entirely new light.
Updated
January 8, 2026 6:33 PM
Serratia marcescens colonies on BTB agar medium. PHOTO: UNSPLASH
Artificial intelligence is beginning to change how scientists understand cancer at the cellular level. In a new collaboration, Bio-Techne Corporation, a global life sciences tools provider, and Nucleai, an AI company specializing in spatial biology for precision medicine, have unveiled data from the SECOMBIT clinical trial that could reshape how doctors predict cancer treatment outcomes. The results, presented at the Society for Immunotherapy of Cancer (SITC) 2025 Annual Meeting, highlight how AI-powered analysis of tumor environments can reveal which patients are more likely to benefit from specific therapies.
Led in collaboration with Professor Paolo Ascierto of the University of Napoli Federico II and Istituto Nazionale Tumori IRCCS Fondazione Pascale, the study explores how spatial biology — the science of mapping where and how cells interact within tissue — can uncover subtle immune behaviors linked to survival in melanoma patients.
Using Bio-Techne’s COMET platform and a 28-plex multiplex immunofluorescence panel, researchers analyzed 42 pre-treatment biopsies from patients with metastatic melanoma, an advanced stage of skin cancer. Nucleai’s multimodal AI platform integrated these imaging results with pathology and clinical data to trace patterns of immune cell interactions inside tumors.
The findings revealed that therapy sequencing significantly influences immune activity and patient outcomes. Patients who received targeted therapy followed by immunotherapy showed stronger immune activation, marked by higher levels of PD-L1+ CD8 T-cells and ICOS+ CD4 T-cells. Those who began with immunotherapy benefited most when PD-1+ CD8 T-cells engaged closely with PD-L1+ CD4 T-cells along the tumor’s invasive edge. Meanwhile, in patients alternating between targeted and immune treatments, beneficial antigen-presenting cell (APC) and T-cell interactions appeared near tumor margins, whereas macrophage activity in the outer tumor environment pointed to poorer prognosis.
“This study exemplifies how our innovative spatial imaging and analysis workflow can be applied broadly to clinical research to ultimately transform clinical decision-making in immuno-oncology”, said Matt McManus, President of the Diagnostics and Spatial Biology Segment at Bio-Techne.
The collaboration between the two companies underscores how AI and high-plex imaging together can help decode complex biological systems. As Avi Veidman, CEO of Nucleai, explained, “Our multimodal spatial operating system enables integration of high-plex imaging, data and clinical information to identify predictive biomarkers in clinical settings. This collaboration shows how precision medicine products can become more accurate, explainable and differentiated when powered by high-plex spatial proteomics – not limited by low-plex or H&E data alone”.
Dr. Ascierto described the SECOMBIT trial as “a milestone in demonstrating the possible predictive power of spatial biomarkers in patients enrolled in a clinical study”.
The study’s broader message is clear: understanding where immune cells are and how they interact inside a tumor could become just as important as knowing what they are. As AI continues to map these microscopic landscapes, oncology may move closer to genuinely personalized treatment — one patient, and one immune network, at a time.