# Designing Environments Conducive to Interpretable Robot Behavior

arXiv: https://arxiv.org/abs/2007.00820 · HTML: https://mlsanity.com/paper/2007.00820/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2020.

## Built on by (most cited first, 8 of 8)

- [Explainable Autonomous Robots: A Survey and Perspective](https://mlsanity.com/paper/2105.02658/) (2021)
- [Constrained Environment Optimization for Prioritized Multi-Agent Navigation](https://mlsanity.com/paper/2305.11260/) (2023)
- [A Unifying Bayesian Formulation of Measures of Interpretability in Human-AI](https://mlsanity.com/paper/2104.10743/) (2021)
- [Co-Optimizing Reconfigurable Environments and Policies for Decentralized Multi-Agent Navigation](https://mlsanity.com/paper/2403.14583/) (2024)
- [STL: Surprisingly Tricky Logic (for System Validation)](https://mlsanity.com/paper/2305.17258/) (2023)
- [Data-Driven Goal Recognition in Transhumeral Prostheses Using Process Mining Techniques](https://mlsanity.com/paper/2309.08106/) (2023)
- [Generalising Planning Environment Redesign](https://mlsanity.com/paper/2402.07799/) (2024)
- [Reducing Human-Robot Goal State Divergence with Environment Design](https://mlsanity.com/paper/2404.15184/) (2024)

## Abstract (arXiv)

Designing robots capable of generating interpretable behavior is a prerequisite for achieving effective human-robot collaboration. This means that the robots need to be capable of generating behavior that aligns with human expectations and, when required, provide explanations to the humans in the loop. However, exhibiting such behavior in arbitrary environments could be quite expensive for robots, and in some cases, the robot may not even be able to exhibit the expected behavior. Given structured environments (like warehouses and restaurants), it may be possible to design the environment so as to boost the interpretability of the robot's behavior or to shape the human's expectations of the robot's behavior. In this paper, we investigate the opportunities and limitations of environment design as a tool to promote a type of interpretable behavior -- known in the literature as explicable behavior. We formulate a novel environment design framework that considers design over multiple tasks and over a time horizon. In addition, we explore the longitudinal aspect of explicable behavior and the trade-off that arises between the cost of design and the cost of generating explicable behavior over a time horizon.