A survey of 94 published safety evaluations for robots and embodied AI, scored for dexterity, cognition and relevance to catastrophic risk. No current safety evaluation combines dexterous manipulation with causal or strategic reasoning.
I want to live in a world in which robots help us live happier, healthier lives.
Writing
all posts →Frontier models that carried out harmful instructions on RoboHarm's robot refuse the same instructions in text and from a camera image. Preliminary results from text and image ablations.
Current evidence on robot scaling laws, open questions, and why scaling laws matter for the safety of physical AI.
Why advanced physical AI poses distinct risks, the questions the field has not answered, and an invitation to work on them.
What makes hard work feel meaningful, and does meaning emerge?
Selected work
all 29 →Shadow Program Inversion with Differentiable Planning: A Framework for Unified Robot Program Parameter and Trajectory Optimization
In 2025 IEEE International Conference on Robotics and Automation (ICRA), May 2025
This paper presents SPI-DP, a novel first-order optimizer capable of optimizing robot programs with respect to both high-level task objectives and motion-level constraints. To that end, we introduce DGPMP2-ND, a differentiable collision-free motion planner for serial N-DoF kinematics, and integrate it into an iterative, gradient-based optimization approach for generic, parameterized robot program representations. SPI-DP allows first-order optimization of planned trajectories and program parameters with respect to objectives such as cycle time or smoothness subject to e.g. collision constraints, while enabling humans to understand, modify or even certify the optimized programs. We provide a comprehensive evaluation on two practical household and industrial applications.
RoboGrind: Intuitive and Interactive Surface Treatment with Industrial Robots
In 2024 IEEE International Conference on Robotics and Automation (ICRA), May 2024
Surface treatment tasks such as grinding, sanding or polishing are a vital step of the value chain in many industries, but are notoriously challenging to automate. We present RoboGrind, an integrated system for the intuitive, interactive automation of surface treatment tasks with industrial robots. It combines a sophisticated 3D perception pipeline for surface scanning and automatic defect identification, an interactive voice-controlled wizard system for the AI-assisted bootstrapping and parameterization of robot programs, and an automatic planning and execution pipeline for force-controlled robotic surface treatment. RoboGrind is evaluated both under laboratory and real-world conditions in the context of refabricating fiberglass wind turbine blades.
Robot Program Parameter Inference via Differentiable Shadow Program Inversion
In 2021 IEEE International Conference on Robotics and Automation (ICRA), May 2021
Challenging manipulation tasks can be solved effectively by combining individual robot skills, which must be parameterized for the concrete physical environment and task at hand. This is time-consuming and difficult for human programmers, particularly for force-controlled skills. To this end, we present Shadow Program Inversion (SPI), a novel approach to infer optimal skill parameters directly from data. SPI leverages unsupervised learning to train an auxiliary differentiable program representation ("shadow program") and realizes parameter inference via gradient-based model inversion. Our method enables the use of efficient first-order optimizers to infer optimal parameters for originally non-differentiable skills, including many skill variants currently used in production. SPI zero-shot generalizes across task objectives, meaning that shadow programs do not need to be retrained to infer parameters for different task variants. We evaluate our methods on three different robots and skill frameworks in industrial and household scenarios. Code and examples are available at https://innolab.artiminds.com/icra2021.