Maple enables robots to explore indoors without training data
MAPLE: Mondrian-Anchored Prior for Learning-free Indoor Exploration
Robotics
Summary
Robots exploring unknown indoor spaces need to decide where to go next even when much of the area is unseen. The authors propose MAPLE, a method that predicts what unseen areas might look like without needing any prior training. MAPLE creates multiple possible maps from current sensor data to help robots choose better paths. Tests show MAPLE helps robots explore more efficiently and competes well with methods that require learning from data.
What this means in practice
- •For robotic system engineers: Enable indoor robots to plan exploration paths using a training-free method that predicts unknown spaces with low computational cost.
- •For autonomous vehicle developers: Support efficient navigation for indoor autonomous vehicles by providing plausible map predictions without reliance on offline training datasets.
Authors
Kelvin Aladum, Nisar Ahmed
Abstract
Robots exploring unknown indoor environments must decide where to move while much of the environment remains unseen. Predicting the occupancy of unseen space beyond the current sensor range can improve these decisions, but recent approaches commonly rely on learned models that require offline training and repeated inference during exploration. We introduce the Mondrian-Anchored Prior for Learning-free Indoor Exploration (MAPLE), a training-free predictive approach that adapts the Mondrian process into an online generative prior conditioned on observed geometric cues in the current partial map. MAPLE generates multiple plausible map hypotheses and evaluates visibility separately within each to estimate frontier gain, preserving differences in predicted visibility across hypotheses. Across KTH floor-plans and real-SLAM environments at multiple sensor ranges, MAPLE consistently improves over non-predictive exploration and remains competitive with learned predictive approaches. Its lightweight procedural construction enables predictive exploration with limited computational resources. Experimental results further show that more accurate map prediction does not necessarily produce better exploration, highlighting the importance of how predictions are represented and used in exploration decisions.