← Back
Home › Systems › Robotics

robot-manipulation

pick-and-place manipulation stack

bin picking, Covariant

SystemTechniques · 16Primitives · 49 robot-manipulation Plc scan cycleembedded · medium: Cyclic read-inputs, execute-logic, write-outputs execution with IEC 61131-3 programsSafety monitor architectureembedded · medium: Independent doer/checker safety monitor that forces a safe state when the main channel misbehavesDomain randomizationmachine-learning · medium: Randomize simulator physics and visuals so policies trained in sim transfer to real robotsImage segmentationmachine-learning · medium: Pixel/instance segmentation networks and promptable segmentation (Mask R-CNN, SAM-style)Imitation learningmachine-learning · medium: Learning policies from demonstrations: behavior cloning, DAgger, covariate shiftObject detectionmachine-learning · medium: A network turns an image into scored, classified boxes in one pass; anchor-based, anchor-free and set-prediction heads differ in how they assign labels and remove duplicates.›Point cloud processingmachine-learning · medium: Voxelization, pillars, k-NN and point networks for lidar perceptionFixed-rate control loopembedded · low: Run a controller at an exact period using absolute deadlines and a fixed dt, so jitter never accumulates and the math stays valid.›Action chunkingmachine-learning · low: Policy predicts a chunk of future actions per step, executed with temporal ensembling for smooth controlRigid-body transforms (SE(3) poses)robotics · low: Represent, compose, invert, integrate and interpolate 3D poses as unit quaternion plus translation, with exp/log maps for small motions and uncertainty.›GJK and EPAphysics · low: GJK decides whether (and how far apart) two convex shapes are from their support functions alone; EPA expands its simplex into penetration depth and normal.›Ransacrobotics · low: Random sample consensus for robust model fitting with outliers (homographies, planes, poses)Transformer blockml-training · low: The decoder-only pre-norm block (attention plus MLP on a residual stream) behind every modern LLM, with exact shapes, parameter, FLOP and KV-cache counts.›Diffusion modelsml-training · low: Train a network to undo Gaussian noise at every noise level, then generate by integrating from pure noise to data; the standard for images, video and audio.›Bounding volume hierarchyphysics · low: Binary tree of nested bounding boxes; prunes overlap and ray queries to O(log n) for any size distribution, and supports cheap insert/remove for moving objects.›Structured light depthrobotics · low: Depth from projected dot patterns or time-of-flight for 3D face captureReal time fieldbusembedded · low: Deterministic cyclic fieldbuses (EtherCAT, PROFINET IRT): on-the-fly frames, distributed clocksWatchdog timerembedded · low: A hardware down-counter that resets the chip unless software proves, in time and in a plausible pattern, that it is still healthy.›End to end protection e2eembedded · low: Per-message counter, ID and CRC over a black channel to detect loss, repetition, corruption, delayMemory protection unitembedded · low: A handful of base/size regions with permissions, checked on every access by the CPU, give microcontroller tasks isolation and stack-overflow traps without an MMU.›Redundancy votingembedded · low: N-modular redundancy and MooN voting (2oo3, TMR) with discrepancy detectionData augmentationmachine-learning · low: Generate label-preserving variants of each training example on the fly to enlarge the effective dataset and bake in invariances.›PRNGs (PCG, xoshiro)numerics · low: Small, fast, statistically strong non-cryptographic generators: PCG32 and xoshiro256**, with seeding, parallel streams and unbiased ranges.›+ 9 more techniques+ 33 more primitives

Similar systems

Share the most building blocks with this one.

robot-policy 20 %humanoid-robot 18 %dimensional-metrology 18 %autonomous-trucking 17 %surgical-robot 17 %