About

Roberto Horowitz is a Professor in the Department of Mechanical Engineering at UC Berkeley and holds the James Fife Endowed Chair in the College of Engineering. He received his B.S. degree with highest honors in 1978 and his Ph.D. degree in 1983, both in mechanical engineering from the University of California at Berkeley. He became a faculty member of the Mechanical Engineering Department in 1982. Dr. Horowitz teaches and conducts research in the areas of adaptive, learning, nonlinear, and optimal control, with applications to Micro-Electromechanical Systems (MEMS), computer disk file systems, robotics, mechatronics, and Intelligent Vehicle and Highway Systems (IVHS). He is a former Chair of the Department of Mechanical Engineering and a former co-director of the Partners for Advanced Transportation Technology (PATH) research center at UC Berkeley. Dr. Horowitz is a member of IEEE and ASME, and has received notable awards including the 2010 ASME Dynamic Systems and Control Division Henry M. Paynter Outstanding Investigator Award and the 2018 ASME Rufus Oldenburger Medal for lifetime achievements in automatic control.

Research topics

• Computer Science
• Artificial Intelligence
• Engineering
• Control engineering
• Automotive engineering
• Computer network
• Telecommunications

Selected publications

• Group-Invariant Unsupervised Skill Discovery: Symmetry-aware Skill Representations for Generalizable Behavior

  ArXiv.org · 2026-01-20

  articleOpen access

  Unsupervised skill discovery aims to acquire behavior primitives that improve exploration and accelerate downstream task learning. However, existing approaches often ignore the geometric symmetries of physical environments, leading to redundant behaviors and sample inefficiency. To address this, we introduce Group-Invariant Skill Discovery (GISD), a framework that explicitly embeds group structure into the skill discovery objective. Our approach is grounded in a theoretical guarantee: we prove that in group-symmetric environments, the standard Wasserstein dependency measure admits a globally optimal solution comprised of an equivariant policy and a group-invariant scoring function. Motivated by this, we formulate the Group-Invariant Wasserstein dependency measure, which restricts the optimization to this symmetry-aware subspace without loss of optimality. Practically, we parameterize the scoring function using a group Fourier representation and define the intrinsic reward via the alignment of equivariant latent features, ensuring that the discovered skills generalize systematically under group transformations. Experiments on state-based and pixel-based locomotion benchmarks demonstrate that GISD achieves broader state-space coverage and improved efficiency in downstream task learning compared to a strong baseline.

  PublisherOA PDF

• Multi-scale Semantics Meet SE(3) Geometry: A Sequence-Aware Hierarchical VLA for Long-Horizon Manipulation

  SSRN Electronic Journal · 2026-01-01

  preprintOpen access
  PublisherDOI

• Group-Invariant Unsupervised Skill Discovery: Symmetry-aware Skill Representations for Generalizable Behavior

  arXiv (Cornell University) · 2026-01-20

  preprintOpen access

  Unsupervised skill discovery aims to acquire behavior primitives that improve exploration and accelerate downstream task learning. However, existing approaches often ignore the geometric symmetries of physical environments, leading to redundant behaviors and sample inefficiency. To address this, we introduce Group-Invariant Skill Discovery (GISD), a framework that explicitly embeds group structure into the skill discovery objective. Our approach is grounded in a theoretical guarantee: we prove that in group-symmetric environments, the standard Wasserstein dependency measure admits a globally optimal solution comprised of an equivariant policy and a group-invariant scoring function. Motivated by this, we formulate the Group-Invariant Wasserstein dependency measure, which restricts the optimization to this symmetry-aware subspace without loss of optimality. Practically, we parameterize the scoring function using a group Fourier representation and define the intrinsic reward via the alignment of equivariant latent features, ensuring that the discovered skills generalize systematically under group transformations. Experiments on state-based and pixel-based locomotion benchmarks demonstrate that GISD achieves broader state-space coverage and improved efficiency in downstream task learning compared to a strong baseline.

  PublisherDOI

• Hybrid Perception and Equivariant Diffusion for Robust Multi-Node Rebar Tying

  ArXiv.org · 2025-08-26

  preprintOpen access

  Rebar tying is a repetitive but critical task in reinforced concrete construction, typically performed manually at considerable ergonomic risk. Recent advances in robotic manipulation hold the potential to automate the tying process, yet face challenges in accurately estimating tying poses in congested rebar nodes. In this paper, we introduce a hybrid perception and motion planning approach that integrates geometry-based perception with Equivariant Denoising Diffusion on SE(3) (Diffusion-EDFs) to enable robust multi-node rebar tying with minimal training data. Our perception module utilizes density-based clustering (DBSCAN), geometry-based node feature extraction, and principal component analysis (PCA) to segment rebar bars, identify rebar nodes, and estimate orientation vectors for sequential ranking, even in complex, unstructured environments. The motion planner, based on Diffusion-EDFs, is trained on as few as 5-10 demonstrations to generate sequential end-effector poses that optimize collision avoidance and tying efficiency. The proposed system is validated on various rebar meshes, including single-layer, multi-layer, and cluttered configurations, demonstrating high success rates in node detection and accurate sequential tying. Compared with conventional approaches that rely on large datasets or extensive manual parameter tuning, our method achieves robust, efficient, and adaptable multi-node tying while significantly reducing data requirements. This result underscores the potential of hybrid perception and diffusion-driven planning to enhance automation in on-site construction tasks, improving both safety and labor efficiency.

  PublisherOA PDFDOI

• Geometric Formulation of Unified Force-Impedance Control on SE(3) for Robotic Manipulators

  ArXiv.org · 2025-04-23

  preprintOpen accessSenior author

  In this paper, we present an impedance control framework on the SE(3) manifold, which enables force tracking while guaranteeing passivity. Building upon the unified force-impedance control (UFIC) and our previous work on geometric impedance control (GIC), we develop the geometric unified force impedance control (GUFIC) to account for the SE(3) manifold structure in the controller formulation using a differential geometric perspective. As in the case of the UFIC, the GUFIC utilizes energy tank augmentation for both force-tracking and impedance control to guarantee the manipulator's passivity relative to external forces. This ensures that the end effector maintains safe contact interaction with uncertain environments and tracks a desired interaction force. Moreover, we resolve a non-causal implementation problem in the UFIC formulation by introducing velocity and force fields. Due to its formulation on SE(3), the proposed GUFIC inherits the desirable SE(3) invariance and equivariance properties of the GIC, which helps increase sample efficiency in machine learning applications where a learning algorithm is incorporated into the control law. The proposed control law is validated in a simulation environment under scenarios requiring tracking an SE(3) trajectory, incorporating both position and orientation, while exerting a force on a surface. The codes are available at https://github.com/Joohwan-Seo/GUFIC_mujoco.

  PublisherOA PDFDOI

• Hybrid Perception and Equivariant Diffusion for Robust Multi-Node Rebar Tying

  2025-08-17 · 2 citations

  article

  Rebar tying is a repetitive but critical task in reinforced concrete construction, typically performed manually at considerable ergonomic risk. Recent advances in robotic manipulation hold the potential to automate the tying process, yet face challenges in accurately estimating tying poses in congested rebar nodes. In this paper, we introduce a hybrid perception and motion planning approach that integrates geometry-based perception with Equivariant Denoising Diffusion on SE(3) (Diffusion-EDFs) to enable robust multi-node rebar tying with minimal training data. Our perception module utilizes density-based clustering (DBSCAN), geometry-based node feature extraction, and principal component analysis (PCA) to segment rebar bars, identify rebar nodes, and estimate orientation vectors for sequential ranking, even in complex, unstructured environments. The motion planner, based on Diffusion-EDFs, is trained on as few as 5–10 demonstrations to generate sequential end-effector poses that optimize collision avoidance and tying efficiency. The proposed system is validated on various rebar meshes, including single-layer, multi-layer, and cluttered configurations, demonstrating high success rates in node detection and accurate sequential tying. Compared with conventional approaches that rely on large datasets or extensive manual parameter tuning, our method achieves robust, efficient, and adaptable multi-node tying while significantly reducing data requirements. This result underscores the potential of hybrid perception and diffusion-driven planning to enhance automation in on-site construction tasks, improving both safety and labor efficiency.

  PublisherDOI

• SE(3)-equivariant Robot Learning and Control: A Tutorial Survey

  International Journal of Control Automation and Systems · 2025-05-14 · 6 citations

  articleSenior author
  PublisherDOI

• SE(3)-Equivariant Robot Learning and Control: A Tutorial Survey

  ArXiv.org · 2025-03-12

  preprintOpen accessSenior author

  Recent advances in deep learning and Transformers have driven major breakthroughs in robotics by employing techniques such as imitation learning, reinforcement learning, and LLM-based multimodal perception and decision-making. However, conventional deep learning and Transformer models often struggle to process data with inherent symmetries and invariances, typically relying on large datasets or extensive data augmentation. Equivariant neural networks overcome these limitations by explicitly integrating symmetry and invariance into their architectures, leading to improved efficiency and generalization. This tutorial survey reviews a wide range of equivariant deep learning and control methods for robotics, from classic to state-of-the-art, with a focus on SE(3)-equivariant models that leverage the natural 3D rotational and translational symmetries in visual robotic manipulation and control design. Using unified mathematical notation, we begin by reviewing key concepts from group theory, along with matrix Lie groups and Lie algebras. We then introduce foundational group-equivariant neural network design and show how the group-equivariance can be obtained through their structure. Next, we discuss the applications of SE(3)-equivariant neural networks in robotics in terms of imitation learning and reinforcement learning. The SE(3)-equivariant control design is also reviewed from the perspective of geometric control. Finally, we highlight the challenges and future directions of equivariant methods in developing more robust, sample-efficient, and multi-modal real-world robotic systems.

  PublisherOA PDFDOI

• Partially Equivariant Reinforcement Learning in Symmetry-Breaking Environments

  arXiv (Cornell University) · 2025-11-30

  preprintOpen access

  Group symmetries provide a powerful inductive bias for reinforcement learning (RL), enabling efficient generalization across symmetric states and actions via group-invariant Markov Decision Processes (MDPs). However, real-world environments almost never realize fully group-invariant MDPs; dynamics, actuation limits, and reward design usually break symmetries, often only locally. Under group-invariant Bellman backups for such cases, local symmetry-breaking introduces errors that propagate across the entire state-action space, resulting in global value estimation errors. To address this, we introduce Partially group-Invariant MDP (PI-MDP), which selectively applies group-invariant or standard Bellman backups depending on where symmetry holds. This framework mitigates error propagation from locally broken symmetries while maintaining the benefits of equivariance, thereby enhancing sample efficiency and generalizability. Building on this framework, we present practical RL algorithms -- Partially Equivariant (PE)-DQN for discrete control and PE-SAC for continuous control -- that combine the benefits of equivariance with robustness to symmetry-breaking. Experiments across Grid-World, locomotion, and manipulation benchmarks demonstrate that PE-DQN and PE-SAC significantly outperform baselines, highlighting the importance of selective symmetry exploitation for robust and sample-efficient RL. Project page: https://pranaboy72.github.io/perl_page/

  PublisherOA PDFDOI

• EquiContact: A Hierarchical SE(3) Vision-to-Force Equivariant Policy for Spatially Generalizable Contact-rich Tasks

  ArXiv.org · 2025-07-15

  preprintOpen accessSenior author

  This paper presents a framework for learning vision-based robotic policies for contact-rich manipulation tasks that generalize spatially across task configurations. We focus on achieving robust spatial generalization of the policy for the peg-in-hole (PiH) task trained from a small number of demonstrations. We propose EquiContact, a hierarchical policy composed of a high-level vision planner (Diffusion Equivariant Descriptor Field, Diff-EDF) and a novel low-level compliant visuomotor policy (Geometric Compliant ACT, G-CompACT). G-CompACT operates using only localized observations (geometrically consistent error vectors (GCEV), force-torque readings, and wrist-mounted RGB images) and produces actions defined in the end-effector frame. Through these design choices, we show that the entire EquiContact pipeline is SE(3)-equivariant, from perception to force control. We also outline three key components for spatially generalizable contact-rich policies: compliance, localized policies, and induced equivariance. Real-world experiments on PiH, screwing, and surface wiping tasks demonstrate a near-perfect success rate and robust generalization to unseen spatial configurations, validating the proposed framework and principles. The experimental videos and more details can be found on the project website: https://equicontact.github.io/EquiContact-website/

  PublisherOA PDFDOI

Recent grants

• SST: Control-oriented Optimal Multisensor Design and Microfabrication for Structural Vibration Suppression in Mechatronic Systems (GOALI)

  NSF · $380k · 2004–2008

• CDI-Type I: Freeway Corridor Operations Design and Implementation

  NSF · $600k · 2009–2014

• Optimal Design and Multiple-input Multiple-output Control Strategies for Media Handling in Copier and Printer Machines

  NSF · $270k · 2003–2009

• CPS: TTP Option: Synergy: Traffic Operating System for Smart Cities

  NSF · $1.1M · 2017–2021

Frequent coauthors

• Perry Y. Li

  42 shared

• Matthew A. Wright

  37 shared

• Jongeun Choi

  Yonsei University

  36 shared

• Gabriel Gomes

  35 shared

• Luis Alvarez

  The University of Texas Rio Grande Valley

  33 shared

• Alex A. Kurzhanskiy

  Center for Information Technology Research in the Interest of Society

  31 shared

• L. Álvarez

  30 shared

• Masayoshi Tomizuka

  30 shared

Labs

• LaboratoriesPI

Education

• Ph.D., Mechanical Engineering

  University of California, Berkeley

  1990

• M.S., Mechanical Engineering

  University of California, Berkeley

  1986

• B.S., Mechanical Engineering

  University of California, Berkeley

  1984

Awards & honors

• 2010 ASME Dynamic Systems and Control Division (DSCD) Henry…
• 2018 ASME Rufus Oldenburger Medal