Heuristic-free Optimization of Force-Controlled Robot Search Strategies in Stochastic Environments
This work addresses the trade-off between robustness and efficiency in robot tasks like peg-in-hole assembly, offering an incremental improvement over heuristic-based methods.
The paper tackled the problem of optimizing robot search strategies in stochastic environments to balance success probability and runtime, introducing a heuristic-free, data-driven approach that achieved adaptive strategies with few real-world measurements.
In both industrial and service domains, a central benefit of the use of robots is their ability to quickly and reliably execute repetitive tasks. However, even relatively simple peg-in-hole tasks are typically subject to stochastic variations, requiring search motions to find relevant features such as holes. While search improves robustness, it comes at the cost of increased runtime: More exhaustive search will maximize the probability of successfully executing a given task, but will significantly delay any downstream tasks. This trade-off is typically resolved by human experts according to simple heuristics, which are rarely optimal. This paper introduces an automatic, data-driven and heuristic-free approach to optimize robot search strategies. By training a neural model of the search strategy on a large set of simulated stochastic environments, conditioning it on few real-world examples and inverting the model, we can infer search strategies which adapt to the time-variant characteristics of the underlying probability distributions, while requiring very few real-world measurements. We evaluate our approach on two different industrial robots in the context of spiral and probe search for THT electronics assembly.