A robot's personality can shape user experience and acceptance in many social robot applications. Allowing users to customize robot personality could help them tailor robot products to their preferences, but it remains unclear whether this customization diminishes perceptions of the robot as a social agent and whether robot form factor influences these effects. We conducted a 2x2 between-subjects study (N = 79) examining robot form factor (humanoid NAO vs. non-humanoid TurtleBot) and personality customizability (customizable vs. non-customizable) during a collaborative event-planning task. Our results reveal that while customization reduced perceived social agency for both robot types, this reduction was particularly evident for humanoid robots. Conversely, personality customization significantly improved human-robot rapport, with this improvement driven primarily by non-humanoid robots. These findings reveal form factor-dependent effects in personality customization, indicating that robot form and customization capabilities yield differential impacts on perceived social agency and human-robot rapport in human-robot interaction design.

We are motivated by the problem of autonomous vehicle performance validation. A key challenge is that an autonomous vehicle requires testing in every kind of driving scenario it could encounter, including rare events, to provide a strong case for safety and show there is no edge-case pathological behavior. Autonomous vehicle companies rely on potentially millions of miles driven in realistic simulation to expose the driving stack to enough miles to estimate rates and severity of collisions. To address scalability and coverage, we propose the use of a behavior foundation model, specifically a masked autoencoder (MAE), trained to reconstruct driving scenarios. We leverage the foundation model in two complementary ways: we (i) use the learned embedding space to group qualitatively similar scenarios together and (ii) fine-tune the model to label scenario difficulty based on the likelihood of a collision upon simulation. We use the difficulty scoring as importance weighting for the groups of scenarios. The result is an approach which can more rapidly estimate the rates and severity of collisions by prioritizing hard scenarios while ensuring exposure to every kind of driving scenario.

Safe local motion planning for autonomous driving in dynamic environments requires forecasting how the scene evolves. Practical autonomy stacks adopt a semantic object-centric representation of a dynamic scene and build object detection, tracking, and prediction modules to solve forecasting. However, training these modules comes at an enormous human cost of manually annotated objects across frames. In this work, we explore future freespace as an alternative representation to support motion planning. Our key intuition is that it is important to avoid straying into occupied space regardless of what is occupying it. Importantly, computing ground-truth future freespace is annotation-free. First, we explore freespace forecasting as a self-supervised learning task. We then demonstrate how to use forecasted freespace to identify collision-prone plans from off-the-shelf motion planners. Finally, we propose future freespace as an additional source of annotation-free supervision. We demonstrate how to integrate such supervision into the learning-based planners. Experimental results on nuScenes and CARLA suggest both approaches lead to a significant reduction in collision rates.1