Competition Results
UM::Autonomy placed 6th overall, and 3rd among American Universities.
RoboBoat 2023: Ocean Exploration
Nathan Benderson Park
Sarasota, Florida
RoboBoat is an international competition where students design, build, and compete with self-driving robotic boats, in a series of tests aimed at challenging teams through a variety autonomous (self-driving) tasks. In 2023, we were joined by 22 other teams from 4 continents.
UM::Autonomy placed 6th overall, and 3rd among American Universities.
Competition Strategy
For this competition season, we tested with the 2022 hull (itself a refurbished 2017 hull) for most of the year, since it was already built. A new hull made of carbon fiber was being built concurrently by the mechanical team. At the last minute, days before departure for the competition, it was ready. The team spent the weekend preparing the new boat for the competition, and thanks to simulator testing, this process went smoothly and few code changes were needed.
Static Judging Criteria
Besides a team's performance autonomously, we are judged on aspects of both our team and the boat.
Design Documentation
The team must prepare a website, a technical design report, and a video for judges to score. These are evaluated based on how well they introduce the team and its structure as well as design considerations of the boat.
Presentation
The team must present to the judges live their decisions leading to the design of the boat.
Other Judging Criteria
Before the boat can participate in an autonomous challenge, several prerequisite activites must be completed.
Static Safety Inspection
As the boats are very high powered, a runaway boat could damage itself and hurt others. Therefore, competition staff ensure that the boat follows several safety rules:
- The boat stops when a physical red button is pressed on the boat
- The boat stops when a remote switch is flipped, or the remote switch loses power or connection
- The boat does not have any sharp edges so that people in the water can touch the boat safely
UM::Autonomy is proud to have been one of the first three teams to pass the safety inspection at the 2023 competition.
Boat Thrust-to-Weight Ratio
The competition rewards fast and light craft. Therefore, a sliding scale is used where points are lost faster the heavier it gets. The boat is weighed and its thrust is measured every day it is entered in the water. In 2023, UM::Autonomy's boat weighed 55 pounds, the lightest weight class.
High Priority Challenges
Navigate the Panama Canal
- Description
- This challenge is mandatory before attempting other tasks. The ASV needs to pass through two sets of gates (a pair of red and green buoys) and starts autonomous navigation at a minimum of 6 ft before the set of gates.
- Analysis
- As it is mandatory, this challenge is of high importance. In 2019, the boat could only successfully pass the navigation channel once out of four qualification runs as a result of a major electrical failure onboard.
- Goal
- 14 out of 15 successful runs
- Post-competition Remarks
- As one of the simplest tasks, this was completed with high success. However, additional tuning was needed upon arrival to the competition site as the boat's computer vision system would occasionally fail to detect a buoy.
Magellan's Route / Count the Manatees & Jellyfish
- Description
- The ASV passes through between multiple sets of gates (pairs of red and green buoys) The ASV also avoids intermittent yellow buoys (jelly fish) and black buoys (manatees) of various sizes and counts them.
- Analysis
- The challenge requires minimal external hardware or software development and mainly just involves careful navigational operability and fine motor control. This challenge could be tested and fine-tuned early in the development process.
- Goal
- 9 out of 10 successful runs
- Post-competition Remarks
- This challenge revealed some disadvantages of our indoors testing area. Specifically, our obstacle-avoidance system decided that the best way to avoid hitting buoys was to go outside of the red-green channel! While technically following our instructions, it didn't score many points. Although we didn't have time to fix that during the competition, the boat did go through several red-green pairs on some runs scoring us important points.
Northern Passage Challenge
- Description
-
The ASV enters the gate buoys, maneuvers around the mark buoy, and exits thought the same
gate buoys, as quickly as possible. The timer starts when the bow (front) crosses the gate
buoys and stops when the stern (back) crosses the gate buoys.
The team colloquially refers to this as the "Speed Challenge".
- Analysis
- Based on the 2019 score-sheet, a time between 25-45s is needed to remain competitive in the Northern Passage challenge, with the fastest 2019 run coming in at 27 seconds.
- Goal
- 9 out of 10 successful runs. We hope for a baseline of 35 seconds, and a goal of 26 seconds.
- Post-competition Remarks
- Another disadvantage of indoors testing was highlighted here: buoy interference. Specifically, our computer vision system had a hard time distinguising the blue buoy (marking where to turn around) from the black buoys (marking an obstacle to avoid in the previous challenge, Magellan's Route). When we tested indoors, we only tested one or two challenges at a time, and with different lighting.
Medium Priority Challenges
Beaching & Inspecting Turtle Nests
- Description
-
Before the time slot starts, teams are assigned a color and must dock at the bay with the
matching color. Once the ASV detects and enters the docking bay, it must report the number
of "eggs" (number of circles) in the nest.
The team colloquially refers to this challenge as "Docking."
- Analysis
- This challenge is a bit more involved in terms of computer and color/shape recognition but does not require external hardware development.
- Goal
- 9 out of 10 successful runs
- Post-competition Remarks
- This task turned out easier than expected. Matching on color rather than number of dots on the board turned out rather easy. Scoring involved simply hitting the docks.
Feed the Fish
- Description
-
The ASV detects the "feeding table" (purple frame), then lines up and shoot three "pellets"
(racquetballs) through the frame into any of the three holes. Points are awarded if the ball
is fired into any of the holes but fewer points are awarded for just landing the ball on the
deck.
The team colloquially refers to this challenge as "Skeeball," the classic arcade game.
- Analysis
- As both the Ponce de Leon (see next) and Feeding the Fish are new challenges, UM::Autonomy chose to only focus on completing the Ponce de Leon challenge this year, though work was done throughout the year to complete the Skeeball task in the future.
- Goal
- N/A
- Post-competition Remarks
- See next task
Ponce de Leon / Fountain of Youth
- Description
-
The ASV detects the target face (blue/white striped) and shoots enough water through the
target to raise the ball above the green line in the pipe. The ASV may pump the water from
the environment or store it on board.
The team colloquially refers to this challenge as "Water Blast."
- Analysis
- This is the first season with this challenge and hardware and software development of external mechanisms pushed back actual testing. Therefore, we knew that immediate mastery of this task would be difficult and time consuming, and should only be attempted after other challenges.
- Goal
- 3 out of 5 successful runs
- Post-competition Remarks
-
Although we had planned to focus on shooting water rather than balls, it turned out that
water leakage was a big worry: if the pump failed and dumped water in the boat's
electronics, we wouldn't be able to compete anymore. As such, we re-focued our effort on
Feed the Fish. We finally had a working ball-shooting system while at the competition site,
but lack of testing time meant that it couldn't be integrated in time.
Both tasks only had three teams that could shoot anything. No teams landed balls in the buckets.
Low Priority Challenges
Ocean Cleanup
- Description
- The ASV detects an underwater pinger which designates the area to collect "debris" (raquetballs) from. The ASV may then use the collected balls as extra balls in the Feed the Fish challenge.
- Analysis
- As this task is a new challenge, UM::Autonomy chose to focus on completing the Ponce de Leon challenge and Feeding the Fish challenge for this year, though work was done throughout the year to complete the Ocean Cleanup task in the future.
- Goal
- N/A
- Post-competition Remarks
- This was one of the hardest challenges this year. Only a couple teams even had the hardware to participate, and none scored points. We will need to evaluate again whether this task is worth pursuing next year.
