Building a Voice-Controlled Robot with Kotlin and LLMs

Building a Voice-Controlled Robot with Kotlin and LLMs Introduction Natural-language interfaces can make robots easier to operate. Instead of selecting individual buttons, an operator can say commands such as asking a robot to move, inspect an area, or report its status. In this tutorial, we will design an Android application that captures speech, sends the text through an LLM-based command parser, and converts the result into validated robot actions. Architecture User Voice ↓ Android Speech Recognition ↓ Command Text ↓ LLM Intent Parser ↓ Structured Robot Command ↓ Safety Validator ↓ Robot Gateway ↓ ROS 2 / Robot The LLM should not directly control motors. It should produce structured intent that a deterministic safety layer validates. Android Voice Input Android provides speech-recognition APIs that can be used to convert spoken commands into text. A simplified flow is: fun onSpeechResult(text: String) { viewModel.processCommand(text) } The ViewModel can then pass the text to the command-processing layer. Command Model Define a strict command structure: sealed interface RobotCommand { data object Stop : RobotCommand data class Move( val direction: String, val distanceMeters: Double ) : RobotCommand data class Rotate( val degrees: Double ) : RobotCommand } Using a structured representation prevents the robotics layer from receiving arbitrary natural-language instructions. LLM Intent Parsing The LLM can transform: "Move forward two meters" into structured data such as: { "command": "move", "direction": "forward", "distance_meters": 2 } Use structured output or a schema-constrained response where the selected LLM/API supports it. Validation Layer Never send the LLM result directly to the robot. Validate: LLM Output ↓ Schema Validation ↓ Range Validation ↓ Robot State Check ↓ Safety Policy ↓ Execution For example: fun validate(command: RobotCommand): Boolean { return when (command) { RobotCommand.Stop -> true is RobotCommand.Move -> command.distanceMeters in 0.0..5.0 is RobotCommand.Rotate -> command.degrees in -180.0..180.0 } } The exact limits should be determined by the robot's capabilities and safety requirements. Robot Gateway After validation, the Android app sends a structured command: { "type": "move", "direction": "forward", "distanceMeters": 2.0 } The gateway converts this command into the appropriate ROS 2 service, action, or topic. Robot Feedback The robot should return status information: { "state": "executing", "battery": 84, "position": { "x": 2.1, "y": 4.3 } } The Android application can show this in a Compose dashboard. Handling Ambiguous Commands Natural language can be ambiguous. For example: "Go over there." The system should not guess what "there" means. Instead, the application can request clarification: "I need a destination before I can move the robot." This is especially important for physical actions. Voice + Vision The system becomes more powerful when voice and vision are combined. For example: User: "Follow the person wearing a red shirt." Voice → Intent Vision → Person Detection ↓ Robot Navigation The LLM can coordinate high-level intent while deterministic robotics components handle perception and navigation. Offline and Cloud Options Speech recognition and LLM inference can be deployed in different ways: Android | +-- Local speech recognition | +-- Cloud LLM or: Android | Local/Edge AI | Robot / Jetson Choose the architecture based on latency, privacy, connectivity, and hardware constraints. Safety Architecture A recommended control hierarchy is: Natural Language ↓ LLM ↓ Structured Intent ↓ Deterministic Planner ↓ Safety Controller ↓ Robot The LLM should remain outside the final safety-critical control loop. Testing Test commands using a simulated robot before physical deployment. Include: - Valid commands - Invalid commands - Ambiguous commands - Extreme values - Network failures - LLM failures - Speech-recognition errors - Emergency stop Conclusion Combining Android, Kotlin, speech recognition, LLMs, and robotics creates a natural interface for Physical AI systems. The key design principle is to use AI for interpretation and high-level planning while deterministic software remains responsible for validation and safe physical execution. This architecture can be extended toward multimodal robot agents that combine voice, vision, maps, sensors, and autonomous task planning. Useful Links SDK Flutter: https://github.com/v-modal/vmodal_sdk_flutter SDK Android: https://github.com/v-modal/vmodal_sdk_android Discord: https://discord.gg/K72z28KUx Top comments (0)