This tracker collects Nvidia and Intel patent filings on teaching robots to grasp objects, navigate around obstacles, correct sensor drift, and learn from their own failures. Together the filings show two chipmakers racing to turn lab demonstrations into robots that behave reliably outside the lab.
80 filings · tracking since Apr 2026 · latest Nov 2026 · updates weekly
based on all tracked filings in this watchlist · refreshes every week
These patents are all about teaching robots to see, feel, and handle objects without falling back on rigid pre-written rules. The contest is over who can make a robot hand or arm work reliably in the messy real world.
Nvidia carries the most weight here by a wide margin, with filings spread across training robots faster, reading instructions, and controlling any robot body type. Samsung is the only other company close, focused heavily on home and arm robots that fix their own mistakes.
a dated entry each week this watchlist moves · older entries stay archived
This week's filings cover two ways to make robot hands move better. Nvidia looks at learning from human hands, while Tesla focuses on how robot fingers are pulled and controlled.
This week's filings all focus on helping robots handle objects more carefully, covering how a robot reaches, grips, reacts to movement, and pays attention to what it holds. Samsung and Nvidia each filed on this topic.
This week's filings focus on robots that figure things out on their own: planning their own setup, learning faster, and updating their maps as they go. Google leads with two of the three applications.
This week's filings cover three core problems: how a robot sees objects, feels what it touches, and figures out what to do in a factory. Nvidia, Tesla, and Google each filed one patent.
Both new filings focus on making robots smarter about physical tasks: one aims to cut down how much a robot needs to practice before it can handle objects, the other helps robots decide where to put things in a warehouse.
This week's filings show Amazon and Google both working on helping robots see and learn. Amazon focuses on building 3D pictures of objects; Google focuses on letting robots draw on past experience.
Sony filed a patent for robot hands that use light to sense touch more precisely. The focus this week is on giving robot fingers a finer ability to feel what they are holding.
Sony and Nvidia both filed this week, with Nvidia leading on four filings. The new work spans teaching robots to read text, feel objects, and test their own software.
This week's three new filings split across two ideas: teaching robots to understand spoken or typed object commands more flexibly, and helping robot hands feel and correct their own grip. Sony filed twice, covering both smoother movement around obstacles and better pressure-aware gripping.
This week's filings lean heavily on Nvidia, which added two patents covering a single AI brain that can run any robot and a system that reads and labels the parts of 3D objects. Sony also joined with a patent for a two-layer artificial skin that helps robots feel touch more accurately.
counts from tracked filings · focus read from each company’s own filings
20 or more filings in the last 8 weeks · 6 to 19 · under 6
the fights inside the fight · each with its three newest filings · new filings join every week
Nvidia 6
Several filings describe using video, including simulated and AI-generated video, to teach robots how to move and act. Others cover keeping moving robot arms from colliding.
Sony 6, Nvidia 5, Samsung 3
These filings focus on how a robot hand figures out what it is holding and adjusts each finger accordingly. They cover everything from thumb design to grip pressure to finger-by-finger control.
Nvidia 8, Google 2, Samsung 1
These filings describe systems where a robot or AI keeps training itself in a circle, learning from failures and improving without stopping. They cover self-correcting loops, teacher-student setups, and round-the-clock training cycles.
Nvidia 3, Samsung 3, Intel 2
These filings cover robots that notice when something has gone wrong and change their plan on the fly, without a person stepping in.
Samsung 4, Nvidia 3, Google 1
These filings describe robots that build and update pictures of the space around them so they can move through it safely. They cover room mapping, choosing the best viewing spot, and tracking where workers are.
Nvidia 2, Google 1, Intel 1
These filings describe ways to tell a robot what to do using spoken words or by copying human body movements directly. They cover voice commands, motion capture, and breaking instructions into steps.
Light inside the sensor picks up small pressure changes, helping a hand tell an egg from a wrench.
Spoken instructions like move left and slow near the edge are treated the same way as a physical demonstration.
The robot finds a clear angle on a TV or phone screen, moves if needed, and then operates it.
Movement is learned instead of scripted, so a robot can shift from waving to dodging a stroller smoothly.
every tracked filing, month by month · counts are USPTO pre-grant publications, one per publication number (an application, not a granted patent)
US 2026/0346473 A1
After years of wiring robot fingers with cables routed through each joint, this filing shows a simpler path: one cable per finger with a floating stopper that engages only when needed, letting the finger curl naturally around whatever it grabs.
US 2026/0346435 A1
A simulation-based teacher program learns human grasping intent from video, then guides robot hands toward the same outcome despite their mechanical limits, letting different hand designs converge on the same task.
US 2026/0340974 A1
Sensor efficiency: robot vision can compress peripheral clutter to low resolution while rendering its own gripper in full detail, cutting processing load substantially.
US 2026/0336105 A1
Within the grasp-and-move challenge, Samsung splits the problem into reaching and gripping phases, each run by its own AI module. A selector switches between them based on the task stage.
US 2026/0339297 A1
Robots that replan mid-task rather than blindly following instructions could recover from unexpected interference, a problem that's plagued factory automation for decades.
US 2026/0316270 A1
A planner that computes optimal sensor calibration paths lets robots figure out load properties on their own, cutting out manual pose-teaching and the risk of collisions during setup.
US 2026/0320402 A1
After millions of attempts to teach robots basic moves, this filing shows how to compress that learning curve by using each failed attempt more efficiently, cutting practice time by a factor of 63 in early tests.
US 2026/0321040 A1
After establishing that robots need visual landmarks to navigate indoors without GPS, this filing shows how to keep those landmarks current as spaces physically change, preventing the robot from getting lost when familiar features disappear or move.
US 2026/0307249 A1
Automated grip-sequence planning eliminates manual coding of in-process repositioning moves, letting robots adapt when parts or grippers change without programmer intervention.
US 2026/0311365 A1
Iterative rendering of object poses against live camera feed bypasses the need to train classifiers on pose detection, instead using visual matching to converge on grip-ready coordinates.
US 2026/0310299 A1
Molding printed sensors into finger and palm shapes lets robots detect grip pressure and object texture without adding bulk, moving beyond simple position feedback to actual tactile sensing during manipulation.
US 2026/0299557 A1
Using a digital twin as reference, the system converts natural language requests into warehouse tasks, letting robots interpret inventory needs and plan their own routes without human direction for each move.
US 2026/0295823 A1
Reducing redundant contact calculations during grasp simulation cuts the computational cost of training without sacrificing real-world accuracy, letting robots practice more scenarios faster.
US 2026/0289242 A1
Separating perception from decision-making lets robots apply learned behaviors across different tasks without retraining from scratch.
US 2026/0284891 A1
Early filings in this tracker focus on robots learning to grip known objects; Amazon's approach adds perception of novel items by reconstructing their full 3D shape from partial views, letting robots handle unfamiliar products without trial-and-error.
US 2026/0276461 A1
Sony's filing swaps traditional strain sensors for light-based sensing, which could let robot fingers feel finer differences in pressure.
US 2026/0268120 A1
Robots that parse natural language commands could work in unstructured spaces without hand-coded coordinates, reducing setup time and expanding where they're useful in real warehouses.
US 2026/0264250 A1
Robots that fuse distance and contact data before committing to a grasp reduce the guesswork baked into vision-only approaches. This filing suggests sensor redundancy as the path to more reliable object handling in unstructured environments.
US 2026/0264237 A1
Controlling force along different axes independently lets robots navigate tight spaces without explicit obstacle instructions, the arm pushes hard in goal directions while yielding passively to constraints.
US 2026/0267781 A1
Testing robot software is slow, inconsistent, and often done by hand. Nvidia is filing a patent for a system that automates the whole process, running robots through tasks and scoring their performance the same way every time.
US 2026/0264239 A1
Robots could learn new tasks from synthetic training footage generated from a single real video, cutting the time needed to gather the hundreds of examples they typically require.
US 2026/0268515 A1
Robots could adjust their grip mid-motion if cameras track object movement across frames instead of just spotting static targets. This builds the continuous 3D awareness needed to handle shifts in position that static snapshots can't catch.
US 2026/0249453 A1
Robots could follow novel object commands without retraining on every variation, letting them generalize from prior grasping experience to new situations.
US 2026/0249470 A1
Sensor drift during insertion: pressure feedback across fingertips lets the robot detect misalignment and self-correct mid-motion, without waiting for mechanical failure to signal the problem.
US 2026/0249451 A1
Robots that navigate tight spaces would gain real-time responsiveness by running slimmer obstacle-detection models instead of full neural networks, cutting both training time and power draw during deployment.
US 2026/0243614 A1
Stacking soft and firm material layers lets robots distinguish touch pressure and location simultaneously, filling a gap in current grip-control systems that confuse gentle contact with forceful squeezing.
US 2026/0245300 A1
Teaching a computer to look at a 3D model of a chair and immediately know which bits are legs, which is the seat, and which is the back turns out to be surprisingly hard. Nvidia's latest patent describes an AI approach that does exactly that, breaking any 3D shape into a tree of labeled pieces.
US 2026/0241554 A1
A unified model trained on multiple body morphologies lets one AI handle humanoids, quadrupeds, and wheeled platforms without retraining from scratch, consolidating what previously required separate control systems for each robot type.
US 2026/0233387 A1
Selecting the best-performing robot AI from dozens of training iterations currently requires manual testing. Nvidia's system automates this grading by running candidate models through standardized tests in simulation and real-world conditions.
US 2026/0233411 A1
Grip adjustment during handling solves a separate problem from initial grasping: robots need feedback loops that let them shift finger pressure mid-lift when an object rotates or proves heavier than expected.
US 2026/0237177 A1
Orienting objects in 3D space from flat camera images lets robot arms position their grippers correctly before attempting a grasp.
US 2026/0228547 A1
Nvidia's filing gives robots a memory of recent actions, so they can correct course mid-task instead of repeating the same mistake.
US 2026/0225261 A1
Where the watchlist has focused on finger coordination, this filing zeroes in on thumb geometry, specifically the multiple rotation axes needed to replicate how a human thumb crosses opposing fingers.
US 2026/0225237 A1
Google's filing has a robot adjust mid-movement based on what its camera sees, instead of following preset coordinates.
US 2026/0225241 A1
Nvidia's filing makes the physics simulation accurate enough that skills a robot learns in simulation carry over to the real world.
US 2026/0220826 A1
Synthetic image generation lets robots learn object recognition without collecting thousands of real-world photos across different angles and lighting. This reduces the time and cost of assembling training datasets for grasping tasks.
US 2026/0208358 A1
Sony's filing keeps jointed robot arms from hitting obstacles while they move, on top of planning the route beforehand.
US 2026/0212192 A1
Distributing simulation across multiple data centers lets the system collect training data from parallel experiments rather than sequential runs, compressing the months of trial-and-error into weeks.
US 2026/0212189 A1
A feedback loop between two AI models lets robots refine their own training data by learning from real-world attempts, then using that data to improve the next round of learning without human labeling.
US 2026/0212190 A1
Nvidia's filing keeps a robot learning while it works, instead of stopping to retrain between tasks.
US 2026/0212199 A1
Continuous motion blending during execution lets robots shift between actions mid-movement rather than completing one scripted gesture before starting the next, reducing the jarring transitions that plague pre-programmed routines.
US 2026/0212191 A1
Generating training video in simulation rather than capturing it from real robots sidesteps the cost and time of collecting actual footage, letting the system iterate through edge cases at scale.
US 2026/0200092 A1
Tracking how object relationships shift in real time lets robots update their next move without replanning from scratch, solving the navigation problem when environments change mid-task.
US 2026/0200471 A1
Robots can now detect when their sensors drift mid-task and recalibrate in real time, letting them keep working through unexpected physical bumps without restarting.
US 2026/0195585 A1
Generating physics-accurate video from text descriptions lets robots learn collision avoidance and object dynamics in simulation before touching real warehouses, compressing months of trial-and-error into synthetic training data.
US 2026/0192452 A1
Within the gripper-control problem, this filing shows how to run reachability and collision-checking together rather than as separate steps, cutting the decision time a robot arm needs before it moves.
US 2026/0196027 A1
A world foundation model generates predicted video of the target task, letting robots preview actions before execution, confirming the tracker's focus on learning from visual simulation rather than trial-and-error in the physical world.
US 2026/0196032 A1
Synthetic video generation skips the physical trial-and-error loop by letting an AI create realistic robot demonstrations from workspace images and task descriptions, then uses those videos as training data.
US 2026/0195951 A1
Where the watchlist has focused on learning from real failures, this filing shows robots could instead practice in physics-accurate simulations, collapsing trial-and-error into virtual space before touching actual objects.
US 2026/0192447 A1
Sensor gloves paired with headset tracking split the workload between hand-detail capture and full-body positioning, letting a human operator demonstrate complex manipulation tasks to a robot in real time rather than programming each movement.
US 2026/0187836 A1
Within the grasp-and-move watchlist, this filing shows how robots can learn placement tasks from minimal human input, moving past the hundreds-of-example bottleneck by extracting spatial logic from a single demonstration video.
US 2026/0186457 A1
A correction layer that monitors prediction errors and updates the physics model between movements, keeping the robot's control calculations aligned with real-world conditions as they drift.
US 2026/0187990 A1
Previous grasp failures often stem from misreading object geometry or category. This filing merges shape and identity recognition into one step, reducing the mismatch errors that cause awkward approaches.
US 2026/0182802 A1
A robot that removes obstacles instead of stopping at them cuts down the trial-and-error cycles needed to navigate real homes. The mechanical gripper solves the navigation problem by making clutter moveable rather than trying to route around it.
US 2026/0183950 A1
Translating natural language commands into robot motion by learning from paired video and voice narration sidesteps the need to manually code movement parameters for each task.
US 2026/0175427 A1
Robots executing fixed plans crash when sensor data degrades mid-task. Intel's filing shows how to reweight a robot's priorities on the fly, trading off task completion speed against uncertainty about what the robot can actually sense in real time.
US 2026/0166747 A1
Decomposing vague commands into executable sequences, finding the gap between "move the cup" and the dozen micro-actions required to actually do it.
US 2026/0169478 A1
A depth camera lets the robot scan multiple height layers at once and select whichever one contains the clearest landmarks for navigation, solving the problem of getting stuck when a single camera angle sees only clutter.
US 2026/0166758 A1
A robot that spreads its fingers before grasping could handle objects ranging from thin cards to wide bottles without reprogramming between tasks, reducing the need for multiple specialized grippers.
US 2026/0169502 A1
The patents so far show robots learning to manipulate physical objects. Samsung's filing extends the problem into the digital area: a robot must read a screen, understand what it shows, and operate touchscreens or remote interfaces as a human would.
US 2026/0165599 A1
Powered joints that enforce correct motion sequences during exercise represent a shift from passive support to active movement correction, addressing how robots learn limb positioning through physical guidance rather than visual observation alone.
US 2026/0166725 A1
A robot that corrects its own mistakes without human intervention moves the grasp problem from initial training to real-world durability, where small execution errors compound into mission failures.
US 2026/0166732 A1
Samsung's filing has a robot replan on the spot when its map of the room turns out to be incomplete, instead of giving up on the task.
US 2026/0158650 A1
When a robot arm gets physically stuck mid-task, it normally needs human rescue. Samsung's filing shows how onboard AI can detect these deadlock states and compute escape paths without outside intervention.
US 2026/0161179 A1
Samsung's filing keeps wheeled robots on curved paths without drifting by controlling each wheel's speed from the planned route.
US 2026/0153883 A1
A robot that stops smoothly instead of lurching to a halt could reliably set down objects without spilling or dropping them, a basic requirement for any real warehouse work.
US 2026/0151914 A1
Samsung's filing lets a robot move its own cameras to see past obstacles, instead of working around blind spots.
US 2026/0154969 A1
Verification loops stand out as the missing piece: Samsung's patent adds machine vision that compares floor conditions before and after cleaning, letting robots detect when stains persist and decide whether to retry a spot.
US 2026/0154645 A1
A central monitoring system tracks worker movement in real time and feeds dynamic route adjustments directly to the robot fleet, replacing the pre-planned paths that create bottlenecks when humans cluster in one area.
US 2026/0151916 A1
A robot that reads human gaze could pick objects from cluttered spaces without needing explicit verbal commands, reducing the real-time communication overhead that slows down human-robot collaboration in actual homes and warehouses.
US 2026/0145333 A1
Simulating touch feedback without perfect object positions pushes training into territory where robots must learn from incomplete sensory data, mirroring real-world grasping constraints.
US 2026/0145332 A1
A two-stage simulation approach separates learning object geometry from learning real-world motor control, letting the robot master spatial reasoning before encountering sensory noise and delays.
US 2026/0145322 A1
The robot grasping problem requires training data that doesn't overwhelm the learning system from the start. Nvidia's approach sequences tasks by difficulty, letting the AI build competence incrementally rather than failing on hard cases too early.
US 2026/0138272 A1
Robots could infer object weight from human posture during handoffs, eliminating the need to sense weight directly at the moment of grasping and reducing grip failures from misjudged force.
US 2026/0138268 A1
Automated detection of human interventions during robot operations creates a continuous feedback loop for retraining without manual annotation, converting real-world failures into training data at scale.
US 2026/0131474 A1
Intel's filing gives robots a memory of the space around them, so they can find their way without constantly repositioning.
US 2026/0131467 A1
Sensor drift compounds during long warehouse runs, forcing robots to periodically recalibrate. Intel's dual-sensor fusion weights each signal's reliability to maintain continuous position accuracy without stopping.
US 2026/0115906 A1
Separating grasp point prediction from grip planning into two distinct neural networks lets each stage specialize rather than forcing one model to solve both problems simultaneously.
US 2026/0115905 A1
Diffusion models, normally used for image generation, retrain here as simulators that generate candidate grasp sequences from scratch, letting the system learn which approaches work before robots try them physically.
US 2026/0115904 A1
A robot trained in simulation can now adjust its own behavior when real-world physics don't match predictions, eliminating the costly trial-and-error phase that usually follows deployment.
They're mostly working on the same core problem: getting robots to reliably grasp objects and move through real environments without constant human correction. The filings show sim-to-real training loops, sensor fusion for drift, and systems that let robots learn from failed attempts. These are research filings, not confirmed products, so they show direction rather than finished technology.
No. A patent filing describes an idea a company wants to protect, not a shipping product. Nvidia and Intel file broadly across grasping, navigation, and perception, and only some of these ideas will end up in real robots. The filings are a useful signal of where engineering attention is going, not a roadmap.
Grasping keeps showing up because picking up an unfamiliar object reliably is still unsolved in robotics. Nvidia has filed multiple grasping approaches, including diffusion-based and teacher-student methods, which suggests the company sees this as worth attacking from several angles at once rather than settling on one method.
Samsung's filings are more mechanical than Nvidia's or Intel's, covering a two-stage braking system for rolling robots and a robot that repositions its own sensor to see around obstacles. That shows the same reliability concerns, staying in control and seeing clearly, showing up in hardware design and not just AI training methods.
Want this weekly breakdown for a company we don't cover? Patentlyze Pro →