BILL

BILL (Bot Intelligent Large capacity Low cost) is a multimodal service robot designed for human-centered environments. It understands people through voice, vision, and movements, enabling natural interaction and autonomous assistance in real-world spaces.

Instead of relying on isolated commands, BILL combines multiple interaction modalities to perceive people, understand intent, and respond in an intuitive and fluid way. Its architecture enables tasks such as reception, people following, objects delivery, and assistance with daily household chores.

Tools & Technologies

BILL is developed using a modern robotics and AI software stack based on ROS 2 Humble, integrating micro-ROS, ROS2 Control, and NAV2 for navigation and motion control.

The system employs SLAM for localization and mapping, RViz 2 for visualization, and Gazebo as the simulation environment. Computer vision includes face recognition with OpenCV, Dlib, and Haar-cascade, object recognition and pose estimation with YOLOv8n, and people tracking using OpenPose.

Speech interaction is enabled through Ollama Qween 0.5b and Piper TTS. The entire stack runs on Ubuntu 22.04.

ACSO

The ACSO – Center of Computer Architecture, Intelligent Systems and Robotics at the State University of Bahia (UNEB) has been participating in RoboCup since 2009.

Through the BahiaRT team, ACSO has competed in leagues such as 2D Soccer Simulation, Mixed Reality, 3D Soccer Simulation, and RoboCup@Home, contributing to research and innovation in robotics and artificial intelligence.

BILL B26FE

The 2026 version of BILL represents a refined evolution of the robot, featuring a redesigned hardware structure.

The robot includes a new articulated neck, a dynamic mouth display synchronized with speech, and a redesigned gripper with additional servos for greater precision. While maintaining the mecanum-based mobility architecture, the wheel system was improved for better stability and maneuverability, resulting in a more compact and adaptable robot.