Jointly optimizing placement and inference for beacon-based localization

The ability of robots to estimate their location is crucial for a wide variety of autonomous operations. In settings where GPS is unavailable, measurements of transmissions from fixed beacons provide an effective means of estimating a robot's location as it navigates. The accuracy of such a beacon-based localization system depends both on how beacons are distributed in the environment, and how the robot's location is inferred based on noisy and potentially ambiguous measurements. We propose an approach for making these design decisions automatically and without expert supervision, by explicitly searching for the placement and inference strategies that, together, are optimal for a given environment. Since this search is computationally expensive, our approach encodes beacon placement as a differential neural layer that interfaces with a neural network for inference. This formulation allows us to employ standard techniques for training neural networks to carry out the joint optimization. We evaluate this approach on a variety of environments and settings, and find that it is able to discover designs that enable high localization accuracy.

Authors

• Charles B. Schaff
• David Yunis
• Ayan Chakrabarti
• Matthew R. Walter

Keywords

• Sensors
• Interference
• Noise measurement
• Robots
• Neural networks
• Channel allocation
• Optimization
• Joint Optimization
• Neural Network
• Network Inference
• Placement Strategy
• Inference Scheme
• Expert Supervision
• Root Mean Square Error
• Series Of Experiments
• Signal Propagation
• Stochastic Gradient Descent
• Local Setting
• Feed-forward Network
• Sensor Networks
• Sensor Measurements
• Localization Task
• Transmission Channel
• Distribution Strategy
• Mapping Unit
• Sensor Noise
• Channel Power
• Received Signal Strength
• Environment Map
• Long Baseline
• Signal Vector
• Gaussian Process Model
• Local Estimates
• Hidden Layer