Author name cluster

Robert Platt

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

1 author row

NeurIPS Conference 2025 Conference Paper

3D Equivariant Visuomotor Policy Learning via Spherical Projection

Boce Hu
Dian Wang
David Klee
Heng Tian
Xupeng Zhu
Haojie Huang
Robert Platt
Robin Walters

Equivariant models have recently been shown to improve the data efficiency of diffusion policy by a significant margin. However, prior work that explored this direction focused primarily on point cloud inputs generated by multiple cameras fixed in the workspace. This type of point cloud input is not compatible with the now-common setting where the primary input modality is an eye-in-hand RGB camera like a GoPro. This paper closes this gap by incorporating into the diffusion policy model a process that projects features from the 2D RGB camera image onto a sphere. This enables us to reason about symmetries in $\mathrm{SO}(3)$ without explicitly reconstructing a point cloud. We perform extensive experiments in both simulation and the real world that demonstrate that our method consistently outperforms strong baselines in terms of both performance and sample efficiency. Our work, $\textbf{Image-to-Sphere Policy}$ ($\textbf{ISP}$), is the first $\mathrm{SO}(3)$-equivariant policy learning framework for robotic manipulation that works using only monocular RGB inputs.

PDF Details

NeurIPS Conference 2025 Conference Paper

A Practical Guide for Incorporating Symmetry in Diffusion Policy

Dian Wang
Boce Hu
Shuran Song
Robin Walters
Robert Platt

Recently, equivariant neural networks for policy learning have shown promising improvements in sample efficiency and generalization, however, their wide adoption faces substantial barriers due to implementation complexity. Equivariant architectures typically require specialized mathematical formulations and custom network design, posing significant challenges when integrating with modern policy frameworks like diffusion-based models. In this paper, we explore a number of straightforward and practical approaches to incorporate symmetry benefits into diffusion policies without the overhead of full equivariant designs. Specifically, we investigate (i) invariant representations via relative trajectory actions and eye-in-hand perception, (ii) integrating equivariant vision encoders, and (iii) symmetric feature extraction with pretrained encoders using Frame Averaging. We first prove that combining eye-in-hand perception with relative or delta action parameterization yields inherent SE(3)-invariance, thus improving policy generalization. We then perform a systematic experimental study on those design choices for integrating symmetry in diffusion policies, and conclude that an invariant representation with equivariant feature extraction significantly improves the policy performance. Our method achieves performance on par with or exceeding fully equivariant architectures while greatly simplifying implementation.

PDF Details

NeurIPS Conference 2025 Conference Paper

Bridging Equivariant GNNs and Spherical CNNs for Structured Physical Domains

Colin Kohler
Purvik Patel
Nathan Vaska
Justin Goodwin
Matthew Jones
Robert Platt
Rajmonda Caceres
Robin Walters

Many modeling tasks from disparate domains can be framed the same way, computing spherical signals from geometric inputs, for example, computing the radar response of different objects or navigating through an environment. This paper introduces G2Sphere, a general method for mapping object geometries to spherical signals. G2Sphere operates entirely in Fourier space, encoding geometric structure into latent Fourier features using equivariant neural networks and outputting the Fourier coefficients of the continuous target signal, which can be evaluated at any resolution. By utilizing a hybrid GNN-spherical CNN architecture, our method achieves much higher frequency output signal than comparable equivariant GNNs and avoids hand-engineered geometry features used previously by purely spherical methods. We perform experiments on various challenging domains including radar response modeling, aerodynamic drag prediction, and policy learning for manipulation and navigation. We find that G2Sphere outperforms competitive baselines in terms of accuracy and inference time, and we demonstrate that equivariance and Fourier features lead to improved sample efficiency and generalization. The source code is available at: https: //github. com/ColinKohler/geometry2sphere.

PDF Details

TMLR Journal 2025 Journal Article

Leveraging Fully-Observable Solutions for Improved Partially-Observable Offline Reinforcement Learning

Chulabhaya Wijesundara
Andrea Baisero
Gregory David Castanon
Alan S Carlin
Robert Platt
Christopher Amato

Offline reinforcement learning (RL) is a popular learning framework for control problems where online interactions with the environment are expensive, risky, or otherwise impractical. Existing offline RL methods commonly assume full observability of the state, and therefore there is a lack of offline RL methods that are specialized for the more general case of partially-observable control. To address this gap, we propose Cross-Observability Conservative Q-Learning (CO-CQL), an offline RL algorithm for partially-observable control that leverages fully-observable expert policies in an asymmetric learning setting. To motivate the use of fully-observable experts for partially-observable control, we formalize Cross-Observability Optimality Ratio (COOR), a theoretical measure of cross-observability that quantifies the benefit of learning asymmetrically from a fully-observable expert, and Cross-Observability Approximation Ratio (COAR), an estimation of COOR computable from trained policies. Our empirical evaluation on a wide variety of partially-observable challenges demonstrates that CO-CQL is able to exploit the guidance of fully-observable experts to outperform other state-of-the-art offline algorithms.

PDF Details

AAMAS Conference 2025 Conference Paper

Leveraging Fully-Observable Solutions for Improved Partially-Observable Offline Reinforcement Learning

Chulabhaya Wijesundara
Andrea Baisero
Gregory Castañón
Alan Carlin
Robert Platt
Christopher Amato

Offline reinforcement learning (RL) is valuable in settings where online interactions with an environment are impractical. While such settings are often partially-observable, existing offline RL methods typically focus on fully-observable (FO) Markov decision processes (MDPs) rather than partially-observable MDPs (POMDPs). To help close that gap, we present an offline RL algorithm for POMDPs that leverages expert policies from simpler, fully-observable versions of environments in an asymmetric learning setting. We provide theoretical grounding for how overlap between MDPs and POMDPs can be exploited to improve learning in the partially-observable setting, and our experiments empirically demonstrate that our method significantly improves performance compared to existing state-ofthe-art MDP offline RL algorithms.

PDF

NeurIPS Conference 2023 Conference Paper

A General Theory of Correct, Incorrect, and Extrinsic Equivariance

Dian Wang
Xupeng Zhu
Jung Yeon Park
Mingxi Jia
Guanang Su
Robert Platt
Robin Walters

Although equivariant machine learning has proven effective at many tasks, success depends heavily on the assumption that the ground truth function is symmetric over the entire domain matching the symmetry in an equivariant neural network. A missing piece in the equivariant learning literature is the analysis of equivariant networks when symmetry exists only partially in the domain. In this work, we present a general theory for such a situation. We propose pointwise definitions of correct, incorrect, and extrinsic equivariance, which allow us to quantify continuously the degree of each type of equivariance a function displays. We then study the impact of various degrees of incorrect or extrinsic symmetry on model error. We prove error lower bounds for invariant or equivariant networks in classification or regression settings with partially incorrect symmetry. We also analyze the potentially harmful effects of extrinsic equivariance. Experiments validate these results in three different environments.

PDF Details

AAMAS Conference 2022 Conference Paper

Tactile Pose Estimation and Policy Learning for Unknown Object Manipulation

Tarik Kelestemur
Robert Platt
Taskin Padir

Object pose estimation methods allow finding locations of objects in unstructured environments. This is a highly desired skill for autonomous robot manipulation as robots need to estimate the precise poses of the objects in order to manipulate them. In this paper, we investigate the problems of tactile pose estimation and manipulation for category-level objects. Our proposed method uses a Bayes filter with a learned tactile observation model and a deterministic motion model. Later, we train policies using deep reinforcement learning where the agents use the belief estimation from the Bayes filter. Our models are trained in simulation and transferred to the real world. We analyze the reliability and the performance of our framework through a series of simulated and real-world experiments and compare our method to the baseline work. Our results show that the learned tactile observation model can localize the pose of novel objects at 2-mm and 1-degree resolution for position and orientation, respectively. Furthermore, we experiment on a bottle opening task where the gripper needs to reach the desired grasp state.

PDF

AAMAS Conference 2021 Conference Paper

Action Priors for Large Action Spaces in Robotics

Ondrej Biza
Dian Wang
Robert Platt
Jan-Willem van de Meent
Lawson L. S. Wong

In robotics, it is often not possible to learn useful policies using pure model-free reinforcement learning without significant reward shaping or curriculum learning. As a consequence, many researchers rely on expert demonstrations to guide learning. However, acquiring expert demonstrations can be expensive. This paper proposes an alternative approach where the solutions of previously solved tasks are used to produce an action prior that can facilitate exploration in future tasks. The action prior is a probability distribution over actions that summarizes the set of policies found solving previous tasks. Our results indicate that this approach can be used to solve robotic manipulation problems that would otherwise be infeasible without expert demonstrations. Source code is available at https: //github. com/ondrejba/action_priors.

PDF

AAAI Conference 2019 Conference Paper

Deictic Image Mapping: An Abstraction for Learning Pose Invariant Manipulation Policies

Robert Platt
Colin Kohler
Marcus Gualtieri

In applications of deep reinforcement learning to robotics, it is often the case that we want to learn pose invariant policies: policies that are invariant to changes in the position and orientation of objects in the world. For example, consider a pegin-hole insertion task. If the agent learns to insert a peg into one hole, we would like that policy to generalize to holes presented in different poses. Unfortunately, this is a challenge using conventional methods. This paper proposes a novel state and action abstraction that is invariant to pose shifts called deictic image maps that can be used with deep reinforcement learning. We provide broad conditions under which optimal abstract policies are optimal for the underlying system. Finally, we show that the method can help solve challenging robotic manipulation problems.

PDF Details

AAMAS Conference 2019 Conference Paper

Online Abstraction with MDP Homomorphisms for Deep Learning

Ondrej Biza
Robert Platt

Abstraction of Markov Decision Processes is a useful tool for solving complex problems, as it can ignore unimportant aspects of an environment, simplifying the process of learning an optimal policy. In this paper, we propose a new algorithm for finding abstract MDPs in environments with continuous state spaces. It is based on MDP homomorphisms, a structure-preserving mapping between MDPs. We demonstrate our algorithm’s ability to learn abstractions from collected experience and show how to reuse the abstractions to guide exploration in new tasks the agent encounters. Our novel task transfer method outperforms baselines based on a deep Qnetwork in the majority of our experiments. The source code is at https: //github. com/ondrejba/aamas_19.

PDF

IJCAI Conference 2018 Conference Paper

Recursive Spoken Instruction-Based One-Shot Object and Action Learning

Matthias Scheutz
Evan Krause
Bradley Oosterveld
Tyler Frasca
Robert Platt

Learning new knowledge from single instructions and being able to apply it immediately is highly desirable for artificial agents. We provide the first demonstration of spoken instruction-based one-shot object and action learning in a cognitive robotic architecture and briefly discuss the architectural modifications required to enable such fast learning, demonstrating the new capabilities on a fully autonomous robot.

PDF Details

AAMAS Conference 2017 Conference Paper

Spoken Instruction-Based One-Shot Object and Action Learning in a Cognitive Robotic Architecture

Matthias Scheutz
Evan Krause
Brad Oosterveld
Tyler Frasca
Robert Platt

Learning new knowledge from single instructions and being able to apply it immediately is a highly desirable capability for artificial agents. We provide the first demonstration of spoken instructionbased one-shot object and action learning in a cognitive robotic architecture and discuss the modifications to several architectural components required to enable such fast learning, demonstrating the new capabilities on two different fully autonomous robots. CCS Concepts •Human-centered computing → Natural language interfaces; •Computing methodologies → Online learning settings;

PDF

AAAI Conference 2005 System Paper

Remote Supervisory Control of a Humanoid Robot

Michael T. Rosenstein
Robert Platt

For this demonstration, participants have the opportunity to control a humanoid robot located hundreds of miles away. The general task is to reach, grasp, and transport various objects in the vicinity of the robot. Although remote “pick-and-place” operations of this sort form the basis of numerous practical applications, they are frequently error-prone and fatiguing for human operators. Participants can experience the relative difficulty of remote manipulation both with and without the use of an assistive interface. This interface simplifies the task by injecting artificial intelligence in key places without seizing higher-level control from the operator. In particular, we demonstrate the benefits of two key components of the system: a video display of predicted operator intentions, and a haptic-based controller for automated grasping.

PDF Details

NeurIPS Conference 2004 Conference Paper

Coarticulation in Markov Decision Processes

Khashayar Rohanimanesh
Robert Platt
Sridhar Mahadevan
Roderic Grupen

We investigate an approach for simultaneously committing to mul- tiple activities, each modeled as a temporally extended action in a semi-Markov decision process (SMDP). For each activity we de- fine a set of admissible solutions consisting of the redundant set of optimal policies, and those policies that ascend the optimal state- value function associated with them. A plan is then generated by merging them in such a way that the solutions to the subordinate activities are realized in the set of admissible solutions satisfying the superior activities. We present our theoretical results and em- pirically evaluate our approach in a simulated domain.

PDF Details