chatgpt News - CNX Software - Embedded Systems News

May 10, 2024May 10, 2024 by Jean-Luc Aufranc (CNXSoft) - No Comments

XGO-Rider is a 2-wheel self-balancing robot with an ESP32 controller plus either a Raspberry Pi CM4 or BBC Micro:bit (Crowdfunding)

XGO-Rider is a two-wheel self-balancing robot with an ESP32 controller for motor and servo control, USB-C charging, etc… and a choice between a Raspberry Pi CM4 module or a BBC Micro:bit board for display, audio, and camera (CM4-only). It’s not the first robot from Luwu Intelligence, since the company launched the XGO-Mini robot dog in 2021, followed by the XGO 2 Raspberry Pi CM4-powered desktop robotic dog with an arm which we reviewed last year. The new XGO-Rider builds on these earlier models but in a different form factor moving from four-legged robots to a 2-wheel self-balancing robot design with many of the same features including AI vision running on the Raspberry Pi CM4. XGO-Rider specifications: Host controller (one or the other) Raspberry Pi CM4 with 2GB RAM + ESP32 for main control, USB-C charging port, DIP switch BBC Micro:bit V2 + ESP32 for main control, USB-C charging port, DIP […]

February 14, 2024 by Jean-Luc Aufranc (CNXSoft) - 6 Comments

Vivid Unit is a low-profile Rockchip RK3399 SBC with an integrated touchscreen display

Rockchip RK3399 SBC integrated touchscreen display

UUGear’s Vivid Unit is a low-profile SBC with an integrated 5.5-inch 1280×720 touchscreen display powered by the older Rockchip RK3399 hexa-core Cortex-A72/A53 SoC coupled with 4GB RAM and a 32GB eMMC flash. The board also comes with gigabit Ethernet and WiFi 4 connectivity, supports M.2 NVMe storage, offers HDMI output and a MIPI CSI camera input, integrates a speaker and a stereo microphone, and allows for expansion through a 40-pin GPIO header and other headers for ADC and USB. Vivid Unit specifications: SoC – Rockchip RK3399 CPU – Hexa-core big.LITTLE processor with 2x Arm Cortex-A72 cores up to 1.8GHz, 4x Arm Cortex-A53 cores up to 1.4GHz GPU – Arm Mali-T860MP4 GPU AI accelerator – 6 TOPS NPU System Memory – 4GB LPDDR4 Storage 32GB eMMC flash M.2 socket for NVMe SSD Display – 5.5-inch touchscreen display with 1280×720 resolution Video Output – HDMI port Camera Input – MIPI CSI camera […]

November 20, 2023 by Jean-Luc Aufranc (CNXSoft) - No Comments

SaraKIT – An Raspberry Pi CM4 board with ChatGPT-based voice control, motor control, and plenty of sensors (Crowdfunding)

SaraKIT is a carrier board for the Raspberry Pi CM4 system-on-module with BLDC motor controllers and a range of sensors for robotics, support for ChatGPT-based voice control through three microphones and a ZL38063 audio chip, and two MIPI CSI connectors for cameras. The versatile board can be used for voice-controlled products, robots, home automation systems, and interfacing with smart home or office devices. The company also developed various demos such as a Smartphone-controlled LEGO RC car, a self-balancing LEGO robot, a pan-and-tilt camera, various AI demos using MediaPipe such as face tracking and object detection, as well as audio demos using ChatGPT, Alexa, and/or Google Home. SaraKIT specifications: Support system-on-modules – Raspberry Pi Compute Module 4 (CM4) with future CM5 compatibility. MCU – Microchip dsPIC33 16-bit microcontroller with 32 KB SRAM for motor control and LSM6DS3TR sensor Audio Microchip ZL38063 (previously MicroSemi) audio processor for microphone arrays. 3x Knowles SPH0655 […]

September 21, 2023October 18, 2023 by Jean-Luc Aufranc (CNXSoft) - 5 Comments

AI in a box offline LLM solution leverages Rockchip RK3588S’ NPU (Crowdfunding)

Useful Sensors “AI in a box” LLM (large language model) solution works offline with complete privacy and leverages the NPU in Rockchip RK3588S processor for conversational AI similar to ChatGPT but without an internet connection or registration required. The AI box prototype currently relies on off-the-shelf hardware, specifically the Radxa ROCK 5A SBC with 8GB RAM, housed in a plastic enclosure, and the code relies on open-source models like Whisper speech-to-text model and Llama2 language models. Besides conversational AI where you can interact with the box as if you were talking to a person, the AI in a Box can also be useful for other use cases: Live Captions – The box can display subtitles/closed captions for a live event or help in situations where people have trouble hearing a conversation using the audio input. Live Translation – It can also translate various languages close to real-time. Simply select […]

September 1, 2023 by Jean-Luc Aufranc (CNXSoft) - 6 Comments

ESP32-S3-BOX-3 devkit comes with 2.4-inch display, dual microphone, PCIe expansion connector

Espressif Systems has launched an update to their ESP32-S3-Box development kit for online and offline voice assistants with the ESP32-S3-BOX-3 devkit that still features a 2.4-inch capacitive touchscreen display with 320×240 resolution, two microphones, a built-in speaker, and a USB-C port, but replaces the PMOD connector by a PCIe connector for various expansion modules. The open-source ESP32-S3 development kit is powered by the ESP32-S3 SoC with AI extensions and can be used to implement all sorts of solutions using the company’s ESP-SR, ESP RainMaker, and Matter solutions such as an offline voice assistant, a chatbot powered by ChatGPT, a handheld gaming console, a tiny robot, a Matter-compatible Smart Home hub, and more. ESP32-S3-BOX-3 specifications: WiSoC – ESP32-S3 dual-core Tensilica LX7 up to 240 MHz with Wi-Fi 4 & Bluetooth 5, AI instructions, 512KB SRAM Memory and Storage – 16MB octal PSRAM and 16MB QSPI flash Display – 2.4-inch capacitive touchscreen […]

May 27, 2023May 27, 2023 by Jean-Luc Aufranc (CNXSoft) - 4 Comments

SenseCAP Indicator D1Pro Review – An ESP32-S3 & RP2040 IoT devkit with a 4-inch display, LoRa connectivity, sensors

The SenseCAP Indicator D1Pro is an IoT development kit based on ESP32-S3 WiFi & BLE chip, a Raspberry Pi RP2040 microcontroller, and offering LoRa connectivity through an SX1262 RF chip. It also features a 4-inch touchscreen display, two Grove interfaces with ADC & I2C, and two USB Type-C ports including one exposing GPIOs, and the D1Pro integrates tVOC and CO2 sensors, plus the kit ships with an external Grove AHT20 TH sensor for temperature and humidity measurements. SenseCAP Indicator D1Pro Features Dual MCUs and GPIO expansion with the Espressif ESP32-S3 and Raspberry Pi RP2040 microcontrollers and support for over 400 Grove-compatible modules. Real-time air quality monitoring thanks to the built-in tVOC and CO2 sensors, and an external Grove AHT20 TH sensor for more precise temperature and humidity readings. Local LoRa Hub for IoT Connectivity thanks to the integrated Semtech SX1262 LoRa chip for connecting LoRa devices to IoT platforms such […]

April 17, 2023April 20, 2023 by Sponsored Post - No Comments

Using ChatGPT for Robotics – Programming myCobot 280 robotic arm with natural language (Sponsored)

ChatGPT AI chatbot can help engineers write programs, and we recently tested it by letting it write a Python program to read data from an I2C accelerometer. But it can be used for more advanced programs and Microsoft Autonomous Systems and Robotics Group used ChatGPT for robotics and programmed robot arms, drones, and home assistant robots intuitively with (human) language. The long-term goal is to let a typical user control/program a robot without having an engineer write code for the system. Microsoft explains that the current robotics pipelines begin with an engineer or technical user that needs to translate the task’s requirements into code for the system. That’s slow, expensive, and inefficient because a user needs to write code, skilled workers are not cheap, and several interactions are required to get things to work properly. With ChatGPT or other large language models (LLM), a user could “program” the robot with […]

April 9, 2023April 11, 2023 by Jean-Luc Aufranc (CNXSoft) - No Comments

Cytron CM4 Maker Board review – Part 2: NVMe SSD, RTC, Buzzer, Grove modules, ChatGPT…

We’ve already checked out Cytron’s CM4 Maker Board kit with a Raspberry Pi CM4 system-on-module and booted the system with the included 32GB “MAKERDISK” Class 10 microSD card preloaded Raspberry Pi OS in the first part of the review. For the second part of the CM4 Maker review, I’ve mostly used the 128GB NVMe SSD provided by the company and played with other features of the board including the RTC, the buzzer, some Seeed Studio grove modules, and even got help from ChatGPT for one of the Python programs I used. Booting Cytron CM4 Maker Board with the “MAKERDISK” NVMe SSD I connected several Grove modules with GPIO and I2C interfaces, a Raspberry Pi Camera Module 3, an Ethernet cable, two RF dongles for a wireless keyboard and mouse, an HDMI cable to a monitor, and finally inserted the provided 5V/3.5A USB-C power adapter. The MAKERDISK SSD comes with Raspberry […]