Luis Pineda

IROS Conference 2025 Conference Paper

Geometric Retargeting: A Principled, Ultrafast Neural Hand Retargeting Algorithm

• Zhao-Heng Yin
• Changhao Wang
• Luis Pineda
• Chaithanya Krishna Bodduluri
• Tingfan Wu
• Pieter Abbeel
• Mustafa Mukadam

We introduce Geometric Retargeting (GeoRT), an ultrafast, and principled neural hand retargeting algorithm for teleoperation, developed as part of our recent Dexterity Gen (DexGen) system [1]. GeoRT converts human finger keypoints to robot hand keypoints at 1KHz, achieving state-of-the-art speed and accuracy with significantly fewer hyperparameters. This high-speed capability enables flexible postprocessing, such as leveraging a foundational controller for action correction like DexGen. GeoRT is trained in an unsupervised manner, eliminating the need for manual annotation of hand pairs. The core of GeoRT lies in novel geometric objective functions that capture the essence of retargeting: preserving motion fidelity, ensuring configuration space (C-space) coverage, maintaining uniform response through high flatness, pinch correspondence and preventing self-collisions. This approach is free from intensive test-time optimization, offering a more scalable and practical solution for real-time hand retargeting.

NeurIPS Conference 2022 Conference Paper

Theseus: A Library for Differentiable Nonlinear Optimization

• Luis Pineda
• Taosha Fan
• Maurizio Monge
• Shobha Venkataraman
• Paloma Sodhi
• Ricky T. Q. Chen
• Joseph Ortiz
• Daniel DeTone

We present Theseus, an efficient application-agnostic open source library for differentiable nonlinear least squares (DNLS) optimization built on PyTorch, providing a common framework for end-to-end structured learning in robotics and vision. Existing DNLS implementations are application specific and do not always incorporate many ingredients important for efficiency. Theseus is application-agnostic, as we illustrate with several example applications that are built using the same underlying differentiable components, such as second-order optimizers, standard costs functions, and Lie groups. For efficiency, Theseus incorporates support for sparse solvers, automatic vectorization, batching, GPU acceleration, and gradient computation with implicit differentiation and direct loss minimization. We do extensive performance evaluation in a set of applications, demonstrating significant efficiency gains and better scalability when these features are incorporated. Project page: https: //sites. google. com/view/theseus-ai/

NeurIPS Conference 2021 Conference Paper

Active 3D Shape Reconstruction from Vision and Touch

• Edward Smith
• David Meger
• Luis Pineda
• Roberto Calandra
• Jitendra Malik
• Adriana Romero Soriano
• Michal Drozdzal

Humans build 3D understandings of the world through active object exploration, using jointly their senses of vision and touch. However, in 3D shape reconstruction, most recent progress has relied on static datasets of limited sensory data such as RGB images, depth maps or haptic readings, leaving the active exploration of the shape largely unexplored. In active touch sensing for 3D reconstruction, the goal is to actively select the tactile readings that maximize the improvement in shape reconstruction accuracy. However, the development of deep learning-based active touch models is largely limited by the lack of frameworks for shape exploration. In this paper, we focus on this problem and introduce a system composed of: 1) a haptic simulator leveraging high spatial resolution vision-based tactile sensors for active touching of 3D objects; 2) a mesh-based 3D shape reconstruction model that relies on tactile or visuotactile signals; and 3) a set of data-driven solutions with either tactile or visuotactile priors to guide the shape exploration. Our framework enables the development of the first fully data-driven solutions to active touch on top of learned models for object understanding. Our experiments show the benefits of such solutions in the task of 3D shape understanding where our models consistently outperform natural baselines. We provide our framework as a tool to foster future research in this direction.

NeurIPS Conference 2021 Conference Paper

K-level Reasoning for Zero-Shot Coordination in Hanabi

• Brandon Cui
• Hengyuan Hu
• Luis Pineda
• Jakob Foerster

The standard problem setting in cooperative multi-agent settings is \emph{self-play} (SP), where the goal is to train a \emph{team} of agents that works well together. However, optimal SP policies commonly contain arbitrary conventions (``handshakes'') and are not compatible with other, independently trained agents or humans. This latter desiderata was recently formalized by \cite{Hu2020-OtherPlay} as the \emph{zero-shot coordination} (ZSC) setting and partially addressed with their \emph{Other-Play} (OP) algorithm, which showed improved ZSC and human-AI performance in the card game Hanabi. OP assumes access to the symmetries of the environment and prevents agents from breaking these in a mutually \emph{incompatible} way during training. However, as the authors point out, discovering symmetries for a given environment is a computationally hard problem. Instead, we show that through a simple adaption of k-level reasoning (KLR) \cite{Costa-Gomes2006-K-level}, synchronously training all levels, we can obtain competitive ZSC and ad-hoc teamplay performance in Hanabi, including when paired with a human-like proxy bot. We also introduce a new method, synchronous-k-level reasoning with a best response (SyKLRBR), which further improves performance on our synchronous KLR by co-training a best response.

ICML Conference 2021 Conference Paper

Off-Belief Learning

• Hengyuan Hu
• Adam Lerer
• Brandon Cui
• Luis Pineda
• Noam Brown
• Jakob N. Foerster

The standard problem setting in Dec-POMDPs is self-play, where the goal is to find a set of policies that play optimally together. Policies learned through self-play may adopt arbitrary conventions and implicitly rely on multi-step reasoning based on fragile assumptions about other agents’ actions and thus fail when paired with humans or independently trained agents at test time. To address this, we present off-belief learning (OBL). At each timestep OBL agents follow a policy $\pi_1$ that is optimized assuming past actions were taken by a given, fixed policy ($\pi_0$), but assuming that future actions will be taken by $\pi_1$. When $\pi_0$ is uniform random, OBL converges to an optimal policy that does not rely on inferences based on other agents’ behavior (an optimal grounded policy). OBL can be iterated in a hierarchy, where the optimal policy from one level becomes the input to the next, thereby introducing multi-level cognitive reasoning in a controlled manner. Unlike existing approaches, which may converge to any equilibrium policy, OBL converges to a unique policy, making it suitable for zero-shot coordination (ZSC). OBL can be scaled to high-dimensional settings with a fictitious transition mechanism and shows strong performance in both a toy-setting and the benchmark human-AI & ZSC problem Hanabi.

JAIR Journal 2019 Journal Article

Probabilistic Planning with Reduced Models

• Luis Pineda
• Shlomo Zilberstein

Reduced models are simplified versions of a given domain, designed to accelerate the planning process. Interest in reduced models has grown since the surprising success of determinization in the first international probabilistic planning competition, leading to the development of several enhanced determinization techniques. To address the drawbacks of previous determinization methods, we introduce a family of reduced models in which probabilistic outcomes are classified as one of two types: primary and exceptional. In each model that belongs to this family of reductions, primary outcomes can occur an unbounded number of times per trajectory, while exceptions can occur at most a finite number of times, specified by a parameter. Distinct reduced models are characterized by two parameters: the maximum number of primary outcomes per action, and the maximum number of occurrences of exceptions per trajectory. This family of reductions generalizes the well-known most-likely-outcome determinization approach, which includes one primary outcome per action and zero exceptional outcomes per plan. We present a framework to determine the benefits of planning with reduced models, and develop a continual planning approach that handles situations where the number of exceptions exceeds the specified bound during plan execution. Using this framework, we compare the performance of various reduced models and consider the challenge of generating good ones automatically. We show that each one of the dimensions---allowing more than one primary outcome or planning for some limited number of exceptions---could improve performance relative to standard determinization. The results place previous work on determinization in a broader context and lay the foundation for a systematic exploration of the space of model reductions.

AAMAS Conference 2019 Conference Paper

Soft Labeling in Stochastic Shortest Path Problems

• Luis Pineda
• Shlomo Zilberstein

The Stochastic Shortest Path (SSP) is an established model for goaldirected probabilistic planning. Despite its broad applicability, wide adoption of the model has been impaired by its high computational complexity. Efforts to address this challenge have produced promising algorithms that leverage two popular mechanisms: labeling and short-sightedness. The resulting algorithms can generate nearoptimal solutions much faster than optimal solvers, albeit at the cost of poor theoretical guarantees. In this work, we introduce a generalization of labeling, called soft labeling, which results in a framework that encompasses a wide spectrum of efficient labeling algorithms, and offers better theoretical guarantees than existing short-sighted labeling approaches. We also propose a novel instantiation of this framework, the SOFT-FLARES algorithm, which achieves state-of-the-art performance on a diverse set of benchmarks.

IJCAI Conference 2017 Conference Paper

Equi-Reward Utility Maximizing Design in Stochastic Environments

• Sarah Keren
• Luis Pineda
• Avigdor Gal
• Erez Karpas
• Shlomo Zilberstein

We present the Equi Reward Utility Maximizing Design (ER-UMD) problem for redesigning stochastic environments to maximize agent performance. ER-UMD fits well contemporary applications that require offline design of environments where robots and humans act and cooperate. To find an optimal modification sequence we present two novel solution techniques: a compilation that embeds design into a planning problem, allowing use of off-the-shelf solvers to find a solution, and a heuristic search in the modifications space, for which we present an admissible heuristic. Evaluation shows the feasibility of the approach using standard benchmarks from the probabilistic planning competition and a benchmark we created for a vacuum cleaning robot setting.

AAAI Conference 2017 Conference Paper

Fast SSP Solvers Using Short-Sighted Labeling

• Luis Pineda
• Kyle Wray
• Shlomo Zilberstein

State-of-the-art methods for solving SSPs often work by limiting planning to restricted regions of the state space. The resulting problems can then be solved quickly, and the process is repeated during execution when states outside the restricted region are encountered. Typically, these approaches focus on states that are within some distance measure of the start state (e. g. , number of actions or probability of being reached). However, these short-sighted approaches make it difficult to propagate information from states that are closer to a goal than to the start state, thus missing opportunities to improve planning. We present an alternative approach in which short-sightedness is used only to determine whether a state should be labeled as solved or not, but otherwise the set of states that can be accounted for during planning is unrestricted. Based on this idea, we propose the FLARES algorithm and show that it performs consistently well on a wide range of benchmark problems.

AAAI Conference 2017 Short Paper

Redesigning Stochastic Environments for Maximized Utility

• Sarah Keren
• Avigdor Gal
• Erez Karpas
• Luis Pineda
• Shlomo Zilberstein

We present the Utility Maximizing Design (UMD) model for optimally redesigning stochastic environments to achieve maximized performance. This model suits well contemporary applications that involve the design of environments where robots and humans co-exist an co-operate, e. g. , vacuum cleaning robot. We discuss two special cases of the UMD model. The first is the equi-reward UMD (ER-UMD) in which the agents and the system share a utility function, such as for the vacuum cleaning robot. The second is the goal recognition design (GRD) setting, discussed in the literature, in which system and agent utilities are independent. To find the set of optimal modifications to apply to a UMD model, we present a generic method, based on heuristic search. After specifying the conditions for optimality in the general case, we present an admissible heuristic for the ER-UMD case. We also present a novel compilation that embeds the redesign process into a planning problem, allowing use of any off-theshelf solver to find the best way to modify an environment when a design budget is specified. Our evaluation shows the feasibility of the approach using standard benchmarks from the probabilistic planning competition.

IJCAI Conference 2016 Conference Paper

Hierarchical Approach to Transfer of Control in Semi-Autonomous Systems

• Kyle Hollins Wray
• Luis Pineda
• Shlomo Zilberstein

Semi-Autonomous Systems (SAS) encapsulate a stochastic decision process explicitly controlled by both an agent and a human, in order to leverage the distinct capabilities of each actor. Planning in SAS must address the challenge of transferring control quickly, safely, and smoothly back-and-forth between the agent and the human. We formally define SAS and the requirements to guarantee that the controlling entities are always able to act competently. We then consider applying the model to Semi-Autonomous VEhicles (SAVE), using a hierarchical approach in which micro-level transfer-of-control actions are governed by a high-fidelity POMDP model. Macro-level path planning in our hierarchical approach is performed by solving a Stochastic Shortest Path (SSP) problem. We analyze the integrated model and show that it provides the required guarantees. Finally, we test the SAVE model using real-world road data from Open Street Map (OSM) within 10 cities, showing the benefits of the collaboration between the agent and human.

AAMAS Conference 2016 Conference Paper

Hierarchical Approach to Transfer of Control in Semi-Autonomous Systems (Extended Abstract)

• Kyle Hollins Wray
• Luis Pineda
• Shlomo Zilberstein

AAAI Conference 2014 Conference Paper

Probabilistic Planning with Reduced Models

• Luis Pineda

IJCAI Conference 2013 Conference Paper

Fault-Tolerant Planning under Uncertainty

• Luis Pineda
• Yi Lu
• Shlomo Zilberstein
• Claudia V. Goldman

A fault represents some erroneous operation of a system that could result from an action selection error or some abnormal condition. We formally define error models that characterize the likelihood of various faults and consider the problem of faulttolerant planning, which optimizes performance given an error model. We show that factoring the possibility of errors significantly degrades the performance of stochastic planning algorithms such as LAO*, because the number of reachable states grows dramatically. We introduce an approach to plan for a bounded number of faults and analyze its theoretical properties. When combined with a continual planning paradigm, the k-fault-tolerant planning method can produce near-optimal performance, even when the number of faults exceeds the bound. Empirical results in two challenging domains confirm the effectiveness of the approach in handling different types of runtime errors.