Map-Predictive Motion Planning in Unknown Environments

Algorithms for motion planning in unknown environments are generally limited in their ability to reason about the structure of the unobserved environment. As such, current methods generally navigate unknown environments by relying on heuristic methods to choose intermediate objectives along frontiers. We present a unified method that combines map prediction and motion planning for safe, time-efficient au-tonomous navigation of unknown environments by dynamically-constrained robots. We propose a data-driven method for predicting the map of the unobserved environment, using the robot's observations of its surroundings as context. These map predictions are then used to plan trajectories from the robot's position to the goal without requiring frontier selection. We applied this map-predictive motion planning strategy to randomly generated winding hallway environments, yielding substantial improvement in trajectory duration over a naïve frontier pursuit method. We also experimentally demonstrate similar performance to methods using more sophisticated fron-tier selection heuristics while significantly reducing computation time.

Authors

• Amine Elhafsi
• Boris Ivanovic
• Lucas Janson
• Marco Pavone 0001

Keywords

• Robots
• Trajectory
• Planning
• Navigation
• Collision avoidance
• Safety
• Cognition
• Path Planning
• Unknown Environment
• Computation Time
• Prediction Map
• Trajectory Planning
• Trajectory Duration
• Intermediate Objective
• Neural Network
• Convolutional Neural Network
• Free Space
• Maximum Speed
• Completion Time
• Grid Cells
• Parametrized
• Predictive Utility
• Spatial Coordinates
• Trajectory Optimization
• Collision Probability
• Representation Of The Environment
• Decoder Network
• Occupancy Grid
• Unknown Regions
• Fully-connected Network
• Speed Profile
• Aggregation Operators
• Unknown Space
• Reference Path
• Objective Function
• Occupancy Probability
• Current Observations