The Solution

RoboCilek turns selective harvesting into a seamless perception-to-cut workflow built for greenhouse realities.

RoboCilek is a purpose-built autonomous strawberry harvesting system, not a generic agricultural machine. We combine advanced camera-based perception, real-time ripeness logic, precision robotic motion, and a unique stem-cut end-effector to identify harvest-ready fruit and collect it without ever touching the berry.

Compact stationary prototype for precision validation Stem-cut harvesting replacing damaging fruit-squeezing Modular control divided cleanly between perception and actuation
Purpose-Built Not generic field machinery

Engineered exclusively for delicate fruit harvesting under tight greenhouse constraints.

Handling Logic Stem-cut, not fruit-grip

The custom end-effector is designed to strictly avoid direct pressure on the berry.

Control Logic High-level intelligence, embedded precision

Smart perception and planning run seamlessly above deterministic, low-level physical actuation.

Operator Experience Simple start-stop interaction

Total accessibility for non-technical users isn’t a feature; it is a fundamental design requirement.

Core Capabilities

A highly coordinated harvesting stack, built intentionally for the field.

Every feature of RoboCilek is a direct response to real farmer needs. Each capability exists solely because it decisively improves harvest quality, operational clarity, or practical fit within real cultivation conditions.

Capability 01

AI-based strawberry detection

Advanced camera-based perception identifies candidate fruit and isolates the exact harvest target before a single motor moves.

Capability 02

Ripeness classification for selectivity

The robot is intelligently designed to harvest only commercially ready fruit, rather than blindly picking anything visible in the frame.

Capability 03

Workspace-aware robotic positioning

A multi-degree robotic arm ensures perfectly controlled motion inside a defined workspace, completely eliminating unsafe reach attempts.

Capability 04

Controlled stem-cut harvesting

The surgical end-effector is built to approach the stem directly, drastically minimizing any contact with the delicate fruit surface.

Capability 05

Battery-powered autonomy

The system operates independently on battery power, removing the need for constant, expensive external infrastructure during operations.

Capability 06

Simple human interaction model

Intuitive start-stop control and clear on-device status feedback ensure the system is immediately understandable for non-specialist operators.

Harvest Flow

From seeing the fruit to cutting the stem: a flawless, validated sequence.

RoboCilek does not rely on vague promises of autonomy. We execute an explicit, bulletproof chain of perception, filtering, coordinate conversion, safety checks, and highly controlled actuation.

01

Capture the scene

The RealSense D435i captures aligned RGB and depth data, allowing the robot to simultaneously assess both visual appearance and physical distance.

02

Find ripe candidates

YOLOv8n-seg generates precise instance masks, while our custom HSV logic strictly verifies that the unripe signal ratio is low enough for a premium harvest.

03

Estimate reliable depth

Depth pixels inside the target mask are processed with robust IQR filtering and reduced to a stable median distance, effectively neutralizing sensor noise.

04

Convert to robot coordinates

Complex deprojection and extrinsic calibration instantly translate camera-space visual information directly into the robot’s physical base frame.

05

Validate motion safety

Strict workspace checks, inverse kinematics, joint limits, and calculated stem offset logic absolutely prevent any unsafe or fruit-damaging movements.

06

Cut and return home

The embedded FSM flawlessly executes the approach, stabilize, cut, and home states in sequence, ensuring every single harvest is deterministic and perfectly repeatable.

Design Logic

Protecting fruit quality by targeting the stem, never squeezing the berry.

True value in harvesting comes from absolute fruit safety. That is why our end-effector strategy is uncompromising: RoboCilek targets the stem with a calculated offset and clean cutting action, intentionally keeping the delicate fruit body completely out of the process.

The danger of fruit-first gripping

Applying direct pressure to strawberries causes bruising, severely shortens shelf life, and immediately strips the fruit of its premium export value.

The superiority of the stem-cut

Our motion objective is surgical: locate the berry, confidently infer the stem approach, and execute the cut while keeping the fruit untouched and safe.

The advantage of compact geometry

Our stationary validation prototype deliberately masters precise execution within a tightly controlled workspace, ensuring reliability before scaling up complexity.

System Stack

Combining reliable hardware building blocks with our custom perception logic.

We strike the perfect engineering balance: proven off-the-shelf components accelerate our physical prototyping, while the core harvesting intelligence and logic remain 100% proprietary to our team.

Vision Layer

RealSense + Segmentation

Intel RealSense D435i provides flawless RGB-depth sensing, backed by YOLOv8n-seg and our StrawDI dataset for rapid instance-level detection.

Decision Layer

Custom Ripeness Engine

Our proprietary HSV-based unripe signal ratio logic acts as the brain, definitively deciding whether a piece of fruit is truly ready for market.

Geometry Layer

Deprojection & Transform

Camera-space coordinates are mathematically converted into precise robot-space targets, strictly validated before a single motor is allowed to move.

Control Layer

Raspberry Pi + Arduino

High-level strategic planning runs powerfully on a Raspberry Pi 5, while fast, deterministic low-level actuation is securely handled by an Arduino Nano.

Mechanical Layer

Custom Arm & End-Effector

Precision servo-driven actuation, custom-engineered geometry, and our specialized stem-cut tool effortlessly translate AI perception into physical action.

Build Philosophy

Agile COTS + Custom Originality

Standardized electronics guarantee rapid iteration, while the critical arm geometry, mounting logic, and harvesting mechanism are entirely team-designed.

Validation And Safety

Built on trust: conservative safety logic and unbreakable repeatability.

We don’t oversell our technology. We deliver strict controlled-environment validation, stable selective harvesting logic, and uncompromising safety behaviors—while remaining totally transparent about our roadmap.

Assurance 01

Reliable perception in a defined workspace

Extensive controlled tests prove our vision system can detect, segment, and classify strawberries with absolute consistency within the prototype envelope.

Assurance 02

Unshakable arm repeatability

Thousands of repeated cycles demonstrate rock-solid positioning behavior, fully supported by conservative motion sequencing and hard joint limits.

Assurance 03

Safety before speed

Rigorous workspace checks, unreachable-target rejection, soft limits, and communication watchdogs virtually eliminate the chance of undefined behavior.

Assurance 04

Zero-damage harvesting objective

Our cutting sequence is explicitly designed around preserving fruit quality, refusing to maximize raw, dangerous speed at the expense of your crop.

Prototype Scope

Proving the core concept today. Engineering the industry standard for tomorrow.

We believe in building in public. Here is exactly what RoboCilek flawlessly executes today, and the ambitious milestones we are targeting next.

What We Prove Today
  • Precision selective harvesting under controlled indoor lighting conditions.
  • Seamless integration of perception, decision-making, and actuation into one coherent stack.
  • Validation that stem-based cutting achieves the zero-damage objective significantly better than direct handling.
  • Highly repeatable motion and cycle timing perfect for validation and commercial demonstration.
What We Build Next
  • Enhanced perception robustness under radically varying lighting and environmental conditions.
  • Advanced inverse kinematics, fluid motion planning, and upgraded end-effector reliability.
  • Deep energy optimization through smarter, more efficient motion sequencing.
  • Aggressive field validation, pilot deployment, and ironclad service-readiness for true grower adoption.
Where This Leads

A highly disciplined prototype with a clear, realistic path to commercial scale.

You’ve seen our coherent perception-to-harvest logic in action. Now, dive deeper into the technical architecture that powers it, or explore how our business model is designed for rapid deployment.