Towards learning hierarchical skills for multi-phase manipulation tasks

Kroemer, Oliver; Daniel, Christian; Neumann, Gerhard; Hoof, Herke van; Peters, Jan

doi:10.1109/icra.2015.7139389

Cited by 103 publications

(83 citation statements)

References 32 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent decades, HMMs have been one of the most popular methods in modeling sequential data such as speech and human behavior recognition [15,16]. In particular, applications of HMMs to robot manipulation is pervasive in domains as diverse as process monitoring [17,18], robot state introspection [9,19], decision-making [20,21], and learning manipulation skill transitions in robot sub-tasks [22,23]. It is possible to use HMMs to perform anomaly detection [17].…”

Section: Multivariate Time-series Modelingmentioning

confidence: 99%

A Latent State-Based Multimodal Execution Monitor with Anomaly Detection and Classification for Robot Introspection

Guan

Rojas

2019

Applied Sciences

View full text Add to dashboard Cite

Robot introspection is expected to greatly aid longer-term autonomy of autonomous manipulation systems. By equipping robots with abilities that allow them to assess the quality of their sensory data, robots can detect and classify anomalies and recover appropriately from common anomalies. This work builds on our previous Sense-Plan-Act-Introspect-Recover (SPAIR) system. We introduce an improved anomaly detector that exploits latent states to monitor anomaly occurrence when robots collaborate with humans in shared workspaces, but also present a multiclass classifier that is activated with anomaly detection. Both implementations are derived from Bayesian non-parametric methods with strong modeling capabilities for learning and inference of multivariate time series with complex and uncertain behavior patterns. In particular, we explore the use of a hierarchical Dirichlet stochastic process prior to learning a Hidden Markov Model (HMM) with a switching vector auto-regressive observation model (sHDP-VAR-HMM). The detector uses a dynamic log-likelihood threshold that varies by latent state for anomaly detection and the anomaly classifier is implemented by calculating the cumulative log-likelihood of testing observation based on trained models. The purpose of our work is to equip the robot with anomaly detection and anomaly classification for the full set of skills associated with a given manipulation task. We consider a human-robot cooperation task to verify our work and measure the robustness and accuracy of each skill. Our improved detector succeeded in detecting 136 common anomalies and 368 nominal executions with a total accuracy of 91.0%. An overall anomaly classification accuracy of 97.1% is derived by performing the anomaly classification on an anomaly dataset that consists of 7 kinds of detected anomalies from a total of 136 anomalies samples.

show abstract

Section: Multivariate Time-series Modelingmentioning

confidence: 99%

A Latent State-Based Multimodal Execution Monitor with Anomaly Detection and Classification for Robot Introspection

Guan

Rojas

2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Beyond anomaly detection, some have worked to identify manipulation skills during execution. In [6], uses a state-based autoregressive HMM to model the skills and transitions of a task. In [12], two independent naïve Bayes classifiers are run to identify skills and anomalies simultaneously.…”

Section: Literature Reviewmentioning

confidence: 99%

Fast, robust, and versatile event detection through HMM belief state gradient measures

Luo¹,

Wu²,

Lin³

et al. 2018

2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)

View full text Add to dashboard Cite

Event detection is a critical feature in data-driven systems as it assists with the identification of nominal and anomalous behavior. Event detection is increasingly relevant in robotics as robots operate with greater autonomy in increasingly unstructured environments. In this work, we present an accurate, robust, fast, and versatile measure for skill and anomaly identification. A theoretical proof establishes the link between the derivative of the log-likelihood of the HMM filtered belief state and the latest emission probabilities. The key insight is the inverse relationship in which gradient analysis is used for skill and anomaly identification. Our measure showed better performance across all metrics than all but one related stateof-the-art works. The result is broadly applicable to domains that use HMMs for event detection. Supplemental information, code, data, and videos can be found at [1].

show abstract

“…In our case, the controller provides them when empirical thresholds were met. Autonomous segmentation approaches can be found in: [2], [3]. Based on these assumptions, the introspection approach seeks to identify the current executing robot-phase given some control goal.…”

Section: Classification Mechanismsmentioning

confidence: 99%

“…If successful, a robot can use this information to reason about its next move: whether it is selecting the next skill to accomplish a task or recovering from abnormal behaviors (internal or external). Much work in the manipulation literature has gone into identifying robot skills that are flexible and reusable [2], [3]; less work has been done in the verification arena, where the robot is able to confirm nominal or abnormal behavior. Even more challenging is identifying not just abnormality but the type of abnormality that is experienced.…”

Section: Introductionmentioning

confidence: 99%

“…The data is then encoded into a series of increasingly abstract layers through a small set of categorical labels yielding an action grammar for that segment of time and, until the end of the task. We assume nominal tasks are composed of a sequence of sub-tasks or phases [2]. For each sub-task the action grammar forms a set of words (sentence) that uniquely describes that phase.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Online robot introspection via wrench-based action grammars

Rojas

Luo

Zhu

et al. 2017

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Abstract-Robotic failure is all too common in unstructured robot tasks. Despite well-designed controllers, robots often fail due to unexpected events. Robots under a sense-planact paradigm do not have an additional loop to check their actions. In this work, we present a principled methodology to bootstrap online robot introspection for contact tasks. In effect, we seek to enable the robot to recognize and expect its behavior, else detect anomalies. We postulated that noisy wrench data inherently contains patterns that can be effectively represented by a vocabulary. The vocabulary is obtained by segmenting and encoding data. And when wrench information represents a sequence of sub-tasks, the vocabulary represents a set of words or sentence and provides a unique identifier. The grammar, which can also include unexpected events, was classified both offline and online for simulated and real robot experiments. Multi-class Support Vector Machines (SVMs) were used offline, while online probabilistic SVMs were used to give temporal confidence to the introspection result. Our work's contribution is the presentation of a generalizable online semantic scheme that enables a robot to understand its high-level state whether nominal or anomalous. It is shown to work in offline and online scenarios for a particularly challenging contact task: snap assemblies. We perform the snap assembly in one-arm simulated and real one-arm experiments and a simulated twoarm experiment. The data set itself is also fully available online and provides a valuable resource by itself for this type of contact task. Our verification mechanism can be used by highlevel planners or reasoning systems to enable intelligent failure recovery or determine the next most optimal manipulation skill to be used. Supplemental information, code, data, and other supporting documentation can be found at [1].

show abstract

Towards learning hierarchical skills for multi-phase manipulation tasks

Cited by 103 publications

References 32 publications

A Latent State-Based Multimodal Execution Monitor with Anomaly Detection and Classification for Robot Introspection

A Latent State-Based Multimodal Execution Monitor with Anomaly Detection and Classification for Robot Introspection

Fast, robust, and versatile event detection through HMM belief state gradient measures

Online robot introspection via wrench-based action grammars

Contact Info

Product

Resources

About