NavWareSet: A Dataset of Socially Compliant and Non-Compliant Robot Navigation

NavWareSet is a novel dataset crafted to advance socially aware robot navigation research. NavWareSet provides multi-modal recordings of both socially compliant and non-compliant robot trajectories in controlled indoor environments. Drawing upon seven carefully selected scenarios, it captures complex human-robot interactions and a range of navigation challenges that mirror realistic social contexts. By including two distinct robot platforms—the Toyota Human Support Robot (HSR) and Clearpath’s Jackal—and systematically varying their navigation behaviors, NavWareSet establishes a rich benchmark for evaluating and training navigation algorithms. With data modalities spanning lidar, RGB-D, stereo vision, odometry, and human position annotations, NavWareSet enables fine-grained analysis of robot decision-making and its impact on human comfort and safety. Ultimately, this dataset offers a versatile resource to develop robust, ethically guided navigation policies and to measure their performance across a spectrum of social situations.