Crush

Built on top of Foxglove Studio using the React Material UI library, the Duke Robotics GUI features a modular and modern design and allows us to easily monitor and control our AUV during pool tests. We can receive real-time updates on the status of our onboard computer, sensors, thrusters, and battery. We can observe the performance of the control system and tune PID constants on-the-fly. We can use a joystick to control the robot directly. Individual panels are organized into layouts and easily deployed using a custom CLI. The GUI also supports replaying recorded ROS bag files for offline debugging and analysis.

Detection

The computer vision (CV) system uses stereo and mono-vision inputs from both our DepthAI and USB cameras to locate items underwater to complete our underwater tasks. For simpler prediction tasks, we employ HSV filtering and contour matching to identify the slalom, path markers, and bin. For more intricate images encountered in the gate, torpedo, and octagon tasks, we utilize YOLO object detection models. Our enhanced CV pipeline seamlessly integrates these methodologies, dynamically adjusting to optimize detection speed and accuracy for various tasks.

Crush relies on many sensors to track both external and internal conditions.

Our primary sensors determine the robot’s state, that being its 6 degrees of freedom: x, y, z, roll, pitch, and yaw. Our IMU, DVL, gyroscope, and pressure sensor are fused in software to provide an accurate state. The IMU, DVL, and gyroscope all have their own direct UART serial connection to the PC, whereas the pressure sensor is read through an Arduino and sent to the main ROS node over USB.

Crush has an onboard sonar, which is connected through USB to the computer.

We also have an internal voltage sensor to monitor the battery and dynamically adjust thruster speed, a temperature sensor to monitor capsule heat, and a humidity sensor to detect water ingress. We also read data from these three internal sensors with an Arduino.

Crush is equipped with two USB cameras mounted at the front of the robot, which we use for visual monitoring during operation. These camera feeds assist our team during testing and troubleshooting.

One of these cameras has been mounted to face downwards at the path markers and the pool floor. This enables Crush to track path markers as well as any competition objects near the floor.

Crush features eight thrusters, and the electrical team provides the hardware abstraction layer used by the controls system.

Each thruster requires a precise PWM signal from the PC. To manage this, we communicate with an Arduino Nano over serial, which interfaces with an I2C multiplexer to control all eight thrusters. The I2C multiplexer is configured to ensure proper PWM outputs are produced based on its internal clock frequency.

In addition to the thrusters, Crush is equipped with a new servo to control a marker dropper. When ROS sends the appropriate commands, we can now deploy team markers from both robots as needed.

Crush has also been fitted with a WaterLinked M16 acoustic modem to enable underwater communication with other robots. The modem’s omnidirectional capabilities allow Oogway to send and receive data from anywhere in the pool without needing to reorient, making it ideal for collaborative, multi-robot tasks.

To support this integration, we developed a custom interface that links the modem to the onboard computer. This interface manages serial communication, publishing incoming messages to a ROS topic and sending outgoing data through a ROS service, as well as ensuring seamless operation within our modular, robot-agnostic system.

To improve serviceability and reduce manufacturing complexity, Crush adopts a consistent mechanical architecture using standardized brackets, repeatable mounting patterns, and a shared rail system. This includes mirrored frame walls and uniform mount geometries, allowing components to be easily swapped or repositioned. These standardized mounts are used for critical hardware like thrusters, sensor brackets, and capsule frames. The integrated rails provide flexible attachment points for internal and external components, supporting future expansion such as additional sensors or task-specific tools. The mirrored layout also enables symmetrical weight distribution, simplifying buoyancy tuning and reducing the need for manual balance adjustments.

Crush’s electrical system is split between two capsules—signal and power—both built on a shared rail-based chassis that allows components to slide into place for organized wiring and efficient use of space. The power capsule houses high-current components like ESCs and the battery, while the signal capsule contains sensors and computing hardware. Components are densely packed using modular sleds, with some mounts supporting multiple devices. Layout revisions improved space use and simplified wiring, and the sliding rail system allows damaged sleds to be easily replaced.

Crush’s frame and case were designed to fully enclose the dual-capsule design and reduce drag. The case follows the contours of the frame and is made from SLS 3D printed nylon to provide optimal strength while keeping the weight down.

Fluid simulations in Ansys Fluent were used to simulate the water flow around the robot, and it was determined that the case reduced drag by 29% as compared to not having a case.

Crush’s new buoyancy blocks were CNC milled to fit exactly inside the case and around the capsules. The Center of Buoyancy was fine-tuned to be directly under the center of mass, which is optimal for staying level when underwater.

The blocks were all designed to be easily removed in under 1 minute, so they do not impede on the capsules when work needs to be done.  Finally, the buoyancy blocks were painted black to boost the aesthetics of the robot!