arXiv subjects

Vikash Kumar

Publications and source records attributed to Vikash Kumar.

At least 55 records · Page 3Linked to original sources

arXiv2023

Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-Grasps

Learning diverse dexterous manipulation behaviors with assorted objects remains an open grand challenge. While policy learning methods offer a powerful avenue to attack this problem, they require extensive per-task engineering and algorithmic tuning. This paper seeks to escape these constraints, by developing a Pre-Grasp informed Dexterous Manipulation (PGDM) framework that generates diverse dexterous manipulation behaviors, without any task-specific reasoning or hyper-parameter tuning. At the core of PGDM is a well known robotics construct, pre-grasps (i.e. the hand-pose preparing for object interaction). This simple primitive is enough to induce efficient exploration strategies for acquiring complex dexterous manipulation behaviors. To exhaustively verify these claims, we introduce TCDM, a benchmark of 50 diverse manipulation tasks defined over multiple objects and dexterous manipulators. Tasks for TCDM are defined automatically using exemplar object trajectories from various sources (animators, human behaviors, etc.), without any per-task engineering and/or supervision. Our experiments validate that PGDM's exploration strategy, induced by a surprisingly simple ingredient (single pre-grasp pose), matches the performance of prior methods, which require expensive per-task feature/reward engineering, expert supervision, and hyper-parameter tuning. For animated visualizations, trained policies, and project code, please refer to: https://pregrasps.github.io/

cs.RO↗

arXiv2023

Zero-Shot Robot Manipulation from Passive Human Videos

Can we learn robot manipulation for everyday tasks, only by watching videos of humans doing arbitrary tasks in different unstructured settings? Unlike widely adopted strategies of learning task-specific behaviors or direct imitation of a human video, we develop a a framework for extracting agent-agnostic action representations from human videos, and then map it to the agent's embodiment during deployment. Our framework is based on predicting plausible human hand trajectories given an initial image of a scene. After training this prediction model on a diverse set of human videos from the internet, we deploy the trained model zero-shot for physical robot manipulation tasks, after appropriate transformations to the robot's embodiment. This simple strategy lets us solve coarse manipulation tasks like opening and closing drawers, pushing, and tool use, without access to any in-domain robot manipulation trajectories. Our real-world deployment results establish a strong baseline for action prediction information that can be acquired from diverse arbitrary videos of human activities, and be useful for zero-shot robotic manipulation in unseen scenes.

cs.RO↗

arXiv2023

Recovering orthogonality from Quasi-type Kernel Polynomials using specific spectral transformations

In this work, the concept of quasi-type Kernel polynomials with respect to a moment functional is introduced. Difference equation satisfied by these polynomials along with the criterion for orthogonality conditions are discussed. The process of recovering orthogonality for the linear combination of a quasi-type kernel polynomial with another orthogonal polynomial, which is identified by involving linear spectral transformation, is provided. This process involves an expression of ratio of iterated kernel polynomials. This lead to considering the limiting case of ratio of kernel polynomials involving continued fractions. Special cases of such ratios in terms of certain continued fractions are exhibited.

math.SP↗

arXiv2022

Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance

Complex and contact-rich robotic manipulation tasks, particularly those that involve multi-fingered hands and underactuated object manipulation, present a significant challenge to any control method. Methods based on reinforcement learning offer an appealing choice for such settings, as they can enable robots to learn to delicately balance contact forces and dexterously reposition objects without strong modeling assumptions. However, running reinforcement learning on real-world dexterous manipulation systems often requires significant manual engineering. This negates the benefits of autonomous data collection and ease of use that reinforcement learning should in principle provide. In this paper, we describe a system for vision-based dexterous manipulation that provides a "programming-free" approach for users to define new tasks and enable robots with complex multi-fingered hands to learn to perform them through interaction. The core principle underlying our system is that, in a vision-based setting, users should be able to provide high-level intermediate supervision that circumvents challenges in teleoperation or kinesthetic teaching which allow a robot to not only learn a task efficiently but also to autonomously practice. Our system includes a framework for users to define a final task and intermediate sub-tasks with image examples, a reinforcement learning procedure that learns the task autonomously without interventions, and experimental results with a four-finger robotic hand learning multi-stage object manipulation tasks directly in the real world, without simulation, manual modeling, or reward engineering.

cs.LG↗

arXiv2022

Cross-Domain Transfer via Semantic Skill Imitation

We propose an approach for semantic imitation, which uses demonstrations from a source domain, e.g. human videos, to accelerate reinforcement learning (RL) in a different target domain, e.g. a robotic manipulator in a simulated kitchen. Instead of imitating low-level actions like joint velocities, our approach imitates the sequence of demonstrated semantic skills like "opening the microwave" or "turning on the stove". This allows us to transfer demonstrations across environments (e.g. real-world to simulated kitchen) and agent embodiments (e.g. bimanual human demonstration to robotic arm). We evaluate on three challenging cross-domain learning problems and match the performance of demonstration-accelerated RL approaches that require in-domain demonstrations. In a simulated kitchen environment, our approach learns long-horizon robot manipulation tasks, using less than 3 minutes of human video demonstrations from a real-world kitchen. This enables scaling robot learning via the reuse of demonstrations, e.g. collected as human videos, for learning in any number of target domains.

cs.LG↗

arXiv2022

MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations

Poor sample efficiency continues to be the primary challenge for deployment of deep Reinforcement Learning (RL) algorithms for real-world applications, and in particular for visuo-motor control. Model-based RL has the potential to be highly sample efficient by concurrently learning a world model and using synthetic rollouts for planning and policy improvement. However, in practice, sample-efficient learning with model-based RL is bottlenecked by the exploration challenge. In this work, we find that leveraging just a handful of demonstrations can dramatically improve the sample-efficiency of model-based RL. Simply appending demonstrations to the interaction dataset, however, does not suffice. We identify key ingredients for leveraging demonstrations in model learning -- policy pretraining, targeted exploration, and oversampling of demonstration data -- which forms the three phases of our model-based RL framework. We empirically study three complex visuo-motor control domains and find that our method is 150%-250% more successful in completing sparse reward tasks compared to prior approaches in the low data regime (100K interaction steps, 5 demonstrations). Code and videos are available at: https://nicklashansen.github.io/modemrl

cs.LG↗

arXiv2022

R3M: A Universal Visual Representation for Robot Manipulation

We study how visual representations pre-trained on diverse human video data can enable data-efficient learning of downstream robotic manipulation tasks. Concretely, we pre-train a visual representation using the Ego4D human video dataset using a combination of time-contrastive learning, video-language alignment, and an L1 penalty to encourage sparse and compact representations. The resulting representation, R3M, can be used as a frozen perception module for downstream policy learning. Across a suite of 12 simulated robot manipulation tasks, we find that R3M improves task success by over 20% compared to training from scratch and by over 10% compared to state-of-the-art visual representations like CLIP and MoCo. Furthermore, R3M enables a Franka Emika Panda arm to learn a range of manipulation tasks in a real, cluttered apartment given just 20 demonstrations. Code and pre-trained models are available at https://tinyurl.com/robotr3m.

cs.RO↗

arXiv2022

CoNMix for Source-free Single and Multi-target Domain Adaptation

This work introduces the novel task of Source-free Multi-target Domain Adaptation and proposes adaptation framework comprising of \textbf{Co}nsistency with \textbf{N}uclear-Norm Maximization and \textbf{Mix}Up knowledge distillation (\textit{CoNMix}) as a solution to this problem. The main motive of this work is to solve for Single and Multi target Domain Adaptation (SMTDA) for the source-free paradigm, which enforces a constraint where the labeled source data is not available during target adaptation due to various privacy-related restrictions on data sharing. The source-free approach leverages target pseudo labels, which can be noisy, to improve the target adaptation. We introduce consistency between label preserving augmentations and utilize pseudo label refinement methods to reduce noisy pseudo labels. Further, we propose novel MixUp Knowledge Distillation (MKD) for better generalization on multiple target domains using various source-free STDA models. We also show that the Vision Transformer (VT) backbone gives better feature representation with improved domain transferability and class discriminability. Our proposed framework achieves the state-of-the-art (SOTA) results in various paradigms of source-free STDA and MTDA settings on popular domain adaptation datasets like Office-Home, Office-Caltech, and DomainNet. Project Page: https://sites.google.com/view/conmix-vcl

cs.LG↗

arXiv2022

RB2: Robotic Manipulation Benchmarking with a Twist

Benchmarks offer a scientific way to compare algorithms using objective performance metrics. Good benchmarks have two features: (a) they should be widely useful for many research groups; (b) and they should produce reproducible findings. In robotic manipulation research, there is a trade-off between reproducibility and broad accessibility. If the benchmark is kept restrictive (fixed hardware, objects), the numbers are reproducible but the setup becomes less general. On the other hand, a benchmark could be a loose set of protocols (e.g. object sets) but the underlying variation in setups make the results non-reproducible. In this paper, we re-imagine benchmarking for robotic manipulation as state-of-the-art algorithmic implementations, alongside the usual set of tasks and experimental protocols. The added baseline implementations will provide a way to easily recreate SOTA numbers in a new local robotic setup, thus providing credible relative rankings between existing approaches and new work. However, these local rankings could vary between different setups. To resolve this issue, we build a mechanism for pooling experimental data between labs, and thus we establish a single global ranking for existing (and proposed) SOTA algorithms. Our benchmark, called Ranking-Based Robotics Benchmark (RB2), is evaluated on tasks that are inspired from clinically validated Southampton Hand Assessment Procedures. Our benchmark was run across two different labs and reveals several surprising findings. For example, extremely simple baselines like open-loop behavior cloning, outperform more complicated models (e.g. closed loop, RNN, Offline-RL, etc.) that are preferred by the field. We hope our fellow researchers will use RB2 to improve their research's quality and rigor.

cs.RO↗

arXiv2022

Real World Offline Reinforcement Learning with Realistic Data Source

Offline reinforcement learning (ORL) holds great promise for robot learning due to its ability to learn from arbitrary pre-generated experience. However, current ORL benchmarks are almost entirely in simulation and utilize contrived datasets like replay buffers of online RL agents or sub-optimal trajectories, and thus hold limited relevance for real-world robotics. In this work (Real-ORL), we posit that data collected from safe operations of closely related tasks are more practical data sources for real-world robot learning. Under these settings, we perform an extensive (6500+ trajectories collected over 800+ robot hours and 270+ human labor hour) empirical study evaluating generalization and transfer capabilities of representative ORL methods on four real-world tabletop manipulation tasks. Our study finds that ORL and imitation learning prefer different action spaces, and that ORL algorithms can generalize from leveraging offline heterogeneous data sources and outperform imitation learning. We release our dataset and implementations at URL: https://sites.google.com/view/real-orl

cs.RO↗

arXiv2022

Revealing the Superior Electrocatalytic Performance of 2D Monolayer WSe$_2$ Transition Metal Dichalcogenide for Efficient H$_2$ Evolution Reaction

H$_2$ evolution reaction (HER) requires an electrocatalyst to reduce the reaction barriers for the efficient production of H$_2$. Platinum-group metal (PGM) elements such as Pt, Pd, etc. and their derivatives show excellent electrocatalytic activity for HER. The high cost and lack of availability of PGM elements bring constraints over their wide commercial applications, so discovering noble metal-free electrocatalysts with lower possible reaction barriers is paramount important. Two-Dimensional Transition Metal Dichalcogenides (2D TMDs) have emerged as a pinnacle group of materials for many potential applications, including HER. In this work, we have computationally designed a pristine 2D monolayer tungsten diselenide (WSe$_2$) TMD using the first principle-based hybrid Density Functional Theory (DFT) to investigate its structural, electronic properties and the electrocatalytic performance for HER. The possible Volmer-Heyrovsky and Volmer-Tafel reaction mechanisms for HER at the W-edge of the active site of WSe$_2$ were studied by using a non-periodic finite molecular cluster model W$_{10}$Se$_{21}$. Our study shows that the pristine 2D monolayer WSe$_2$ follows either the Volmer-Heyrovsky or the Volmer-Tafel reaction mechanisms with a single-digit low reaction barrier about 6.11, 8.41 and 6.61 kcal/mol during the solvent phase calculations of H-migration, Heyrovsky and Tafel transition (TS) states, respectively. The lower reaction barriers, high turnover frequency (TOF) ~ 4.24 x $10^6$ sec$^{-1}$ and 8.86 x $10^7$ sec$^{-1}$ during the Heyrovsky and Tafel reaction steps and the low Tafel slope 29.58 mV.dec$^{-1}$ confirm that the pristine 2D monolayer WSe$_2$ might be a promising alternative to PGM based electrocatalyst.

cond-mat.mtrl-sci↗

arXiv2022

MyoSuite -- A contact-rich simulation suite for musculoskeletal motor control

Embodied agents in continuous control domains have had limited exposure to tasks allowing to explore musculoskeletal properties that enable agile and nimble behaviors in biological beings. The sophistication behind neuro-musculoskeletal control can pose new challenges for the motor learning community. At the same time, agents solving complex neural control problems allow impact in fields such as neuro-rehabilitation, as well as collaborative-robotics. Human biomechanics underlies complex multi-joint-multi-actuator musculoskeletal systems. The sensory-motor system relies on a range of sensory-contact rich and proprioceptive inputs that define and condition muscle actuation required to exhibit intelligent behaviors in the physical world. Current frameworks for musculoskeletal control do not support physiological sophistication of the musculoskeletal systems along with physical world interaction capabilities. In addition, they are neither embedded in complex and skillful motor tasks nor are computationally effective and scalable to study large-scale learning paradigms. Here, we present MyoSuite -- a suite of physiologically accurate biomechanical models of elbow, wrist, and hand, with physical contact capabilities, which allow learning of complex and skillful contact-rich real-world tasks. We provide diverse motor-control challenges: from simple postural control to skilled hand-object interactions such as turning a key, twirling a pen, rotating two balls in one hand, etc. By supporting physiological alterations in musculoskeletal geometry (tendon transfer), assistive devices (exoskeleton assistance), and muscle contraction dynamics (muscle fatigue, sarcopenia), we present real-life tasks with temporal changes, thereby exposing realistic non-stationary conditions in our tasks which most continuous control benchmarks lack.

cs.RO↗

arXiv2022

Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?

Task specification is at the core of programming autonomous robots. A low-effort modality for task specification is critical for engagement of non-expert end-users and ultimate adoption of personalized robot agents. A widely studied approach to task specification is through goals, using either compact state vectors or goal images from the same robot scene. The former is hard to interpret for non-experts and necessitates detailed state estimation and scene understanding. The latter requires the generation of desired goal image, which often requires a human to complete the task, defeating the purpose of having autonomous robots. In this work, we explore alternate and more general forms of goal specification that are expected to be easier for humans to specify and use such as images obtained from the internet, hand sketches that provide a visual description of the desired task, or simple language descriptions. As a preliminary step towards this, we investigate the capabilities of large scale pre-trained models (foundation models) for zero-shot goal specification, and find promising results in a collection of simulated robot manipulation tasks and real-world datasets.

cs.RO↗

arXiv2022

Curiosity Driven Self-supervised Tactile Exploration of Unknown Objects

Intricate behaviors an organism can exhibit is predicated on its ability to sense and effectively interpret complexities of its surroundings. Relevant information is often distributed between multiple modalities, and requires the organism to exhibit information assimilation capabilities in addition to information seeking behaviors. While biological beings leverage multiple sensing modalities for decision making, current robots are overly reliant on visual inputs. In this work, we want to augment our robots with the ability to leverage the (relatively under-explored) modality of touch. To focus our investigation, we study the problem of scene reconstruction where touch is the only available sensing modality. We present Tactile Slam (tSLAM) -- which prepares an agent to acquire information seeking behavior and use implicit understanding of common household items to reconstruct the geometric details of the object under exploration. Using the anthropomorphic `ADROIT' hand, we demonstrate that tSLAM is highly effective in reconstructing objects of varying complexities within 6 seconds of interactions. We also established the generality of tSLAM by training only on 3D Warehouse objects and testing on ContactDB objects.

cs.RO↗

arXiv2022

Policy Architectures for Compositional Generalization in Control

Many tasks in control, robotics, and planning can be specified using desired goal configurations for various entities in the environment. Learning goal-conditioned policies is a natural paradigm to solve such tasks. However, current approaches struggle to learn and generalize as task complexity increases, such as variations in number of environment entities or compositions of goals. In this work, we introduce a framework for modeling entity-based compositional structure in tasks, and create suitable policy designs that can leverage this structure. Our policies, which utilize architectures like Deep Sets and Self Attention, are flexible and can be trained end-to-end without requiring any action primitives. When trained using standard reinforcement and imitation learning methods on a suite of simulated robot manipulation tasks, we find that these architectures achieve significantly higher success rates with less data. We also find these architectures enable broader and compositional generalization, producing policies that extrapolate to different numbers of entities than seen in training, and stitch together (i.e. compose) learned skills in novel ways. Videos of the results can be found at https://sites.google.com/view/comp-gen-rl.

cs.LG↗

arXiv2021

RRL: Resnet as representation for Reinforcement Learning

The ability to autonomously learn behaviors via direct interactions in uninstrumented environments can lead to generalist robots capable of enhancing productivity or providing care in unstructured settings like homes. Such uninstrumented settings warrant operations only using the robot's proprioceptive sensor such as onboard cameras, joint encoders, etc which can be challenging for policy learning owing to the high dimensionality and partial observability issues. We propose RRL: Resnet as representation for Reinforcement Learning -- a straightforward yet effective approach that can learn complex behaviors directly from proprioceptive inputs. RRL fuses features extracted from pre-trained Resnet into the standard reinforcement learning pipeline and delivers results comparable to learning directly from the state. In a simulated dexterous manipulation benchmark, where the state of the art methods fail to make significant progress, RRL delivers contact rich behaviors. The appeal of RRL lies in its simplicity in bringing together progress from the fields of Representation Learning, Imitation Learning, and Reinforcement Learning. Its effectiveness in learning behaviors directly from visual inputs with performance and sample efficiency matching learning directly from the state, even in complex high dimensional domains, is far from obvious.

cs.RO↗

arXiv2021

Deep Neural Network Approach to Estimate Early Worst-Case Execution Time

Estimating Worst-Case Execution Time (WCET) is of utmost importance for developing Cyber-Physical and Safety-Critical Systems. The system's scheduler uses the estimated WCET to schedule each task of these systems, and failure may lead to catastrophic events. It is thus imperative to build provably reliable systems. WCET is available to us in the last stage of systems development when the hardware is available and the application code is compiled on it. Different methodologies measure the WCET, but none of them give early insights on WCET, which is crucial for system development. If the system designers overestimate WCET in the early stage, then it would lead to the overqualified system, which will increase the cost of the final product, and if they underestimate WCET in the early stage, then it would lead to financial loss as the system would not perform as expected. This paper estimates early WCET using Deep Neural Networks as an approximate predictor model for hardware architecture and compiler. This model predicts the WCET based on the source code without compiling and running on the hardware architecture. Our WCET prediction model is created using the Pytorch framework. The resulting WCET is too erroneous to be used as an upper bound on the WCET. However, getting these results in the early stages of system development is an essential prerequisite for the system's dimensioning and configuration of the hardware setup.

cs.SE↗

arXiv2021

Dynamics of thermal and wetting footprint of a volatile droplet during Leidenfrost transition

The levitation of a volatile droplet on a highly superheated surface is known as the Leidenfrost effect. Wetting state during transition from full wetting of a surface by a droplet at room temperature to Leidenfrost bouncing, i.e., zero-wetting at high superheating, is not fully understood. Here, visualizations of droplet thermal and wetting footprint in the Leidenfrost transition state are presented using two optical techniques: mid-infrared thermography and wetting sensitive total internal reflection imaging under carefully selected experimental conditions, impact Weber number < 10 and droplet diameter < capillary length, using an indium-tin-oxide coated sapphire heater. The experimental regime was designed to create relatively stable droplet dynamics, where the effects of oscillatory and capillary instabilities were minimized. The thermography for ethanol droplet in Leidenfrost transition state (superheat range of 82K-97K) revealed thermal footprint with a central hot zone surrounded by a cooler periphery, indicative of a partial wetting state during Leidenfrost transition. High-speed total internal reflection imaging also confirmed the partial wetting footprint such that there are wetting areas around a central non-wetting zone. Result presented here using ethanol as a test fluid shed light on the geometry and dynamics of a volatile droplet footprint in Leidenfrost transition state.

physics.flu-dyn↗