Interpretable Trade-offs Between Robot Task Accuracy and Compute Efficiency
This work addresses the challenge of efficiently allocating computational resources in robotics, which is incremental as it builds on existing model selection concepts.
The paper tackles the model selection problem for robots by proposing an optimal solution that balances task accuracy and compute efficiency, demonstrating its applicability to perception and navigation tasks with concrete examples.
A robot can invoke heterogeneous computation resources such as CPUs, cloud GPU servers, or even human computation for achieving a high-level goal. The problem of invoking an appropriate computation model so that it will successfully complete a task while keeping its compute and energy costs within a budget is called a model selection problem. In this paper, we present an optimal solution to the model selection problem with two compute models, the first being fast but less accurate, and the second being slow but more accurate. The main insight behind our solution is that a robot should invoke the slower compute model only when the benefits from the gain in accuracy outweigh the computational costs. We show that such cost-benefit analysis can be performed by leveraging the statistical correlation between the accuracy of fast and slow compute models. We demonstrate the broad applicability of our approach to diverse problems such as perception using neural networks and safe navigation of a simulated Mars rover.