Publications

Preparing Software Engineers to Develop Robot Systems

Carl Hildebrandt, Meriel von Stein, Trey Woodlief, Sebastian Elbaum

Most undergraduates are not equipped to manage the unique challenges in developing software for modern robots, despite rapid expansion of the field. We here introduce a course we have designed and delivered to better prepare students to develop software for robot systems. It emphasizes the distinctive challenges of software development…
Read more

Download: [Paper] [Artifact]

PhysCov: Physical Test Coverage for Autonomous Vehicles

Carl Hildebrandt, Meriel von Stein, Sebastian Elbaum

Adequately covering the behaviors of autonomous vehicles ($AV$) is fundamental in their validation. However, quantifying such coverage is challenging as the $AV$s’ behavior is influenced by its physical environment that is often large and highly complex. This work builds on the insights that data sensed by the $AV$ provides a…
Read more

Beyond DNN Silo-Testing: Integrating Autonomous System State

Meriel von Stein, David Shriver, Sebastian Elbaum

Adversarial testing tends to focus on DNNs in isolation, to the exclusion of the full system state and system behaviors resulting from sequences of DNN output. In this work we propose a more holistic approach to DNN testing that accounts for the effects of perturbations on the system state. Our…
Read more

Download: [Paper] [Poster]

Automated Environment Reduction for Debugging Robotic Systems

Meriel von Stein, Sebastian Elbaum

Complex environments can cause robots to fail. Identifying the key elements of the environment associated with such failures is critical for faster fault isolation and, ultimately, debugging those failures. In this work we present the first automated approach for reducing the environment in which a robot failed. Similar to software…
Read more

Download: [Paper] [Tool] [Video]

Probabilistic Conditional System Invariant Generation with Bayesian Inference

Meriel von Stein, Sebastian Elbaum, Lu Feng, Shili Sheng

Probabilistic invariants can encode a family of conditional patterns, are generated using Bayesian inference to leverage observed trace data against priors gleaned from previous experience and expert knowledge, and are ranked based on their surprise value and information content. Our studies on two semi-autonomous mobile robotic systems show how the…
Read more

Download: [Paper]

Implicit Invariants for Relational Data Structures

Meriel von Stein

Robotics utilizes algorithms for control, localization, and navigation that rely heavily on complex data structures such as matrices and graphs. The values of these data structures are the result of interleaved controllers and complex interactions between equations that are difficult to parameterize as they relate to observed behavior. This makes…
Read more

Download: [Presentation] [Paper]