Towards Intuitive Robot Programming Using Finite State Automata

Sauer, Lukas; Henrich, Dominik; Martens, Wim

doi:10.1007/978-3-030-30179-8_25

Cited by 6 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…FSA sering diterapkan dalam pengolahan teks seperti analisis tulisan [24][25][26], pemisahan kata [27], kesamaan dokumen [28], grammar [29], spelling [30], dan penerjemah [31], [32]. Beberapa penelitian lain juga menggunakan FSA sebagai sistem pendeteksi/diagnosa [33][34][35][36][37], kontrol/otomatisasi [38][39][40][41][42] dan pengolahan image/ watermarking [43], [44].…”

Section: Pendahuluanunclassified

Deteksi Serangan Denial of Service pada Internet of Things Menggunakan Finite-State Automata

Antony

Gustriansyah

2021

matrik

View full text Add to dashboard Cite

Internet of things memiliki kemampuan untuk menghubungkan obyek pintar dan memungkinkan mereka untuk berinteraksi dengan lingkungan dan peralatan komputasi cerdas lainnya melalui jaringan internet. Namun belakangan ini, keamanan jaringan internet of things mendapat ancaman akibat serangan cyber yang dapat menembus perangkat internet of things target dengan menggunakan berbagai serangan denial of service. Penelitian ini bertujuan untuk mendeteksi dan mencegah serangan denial of service berupa synchronize flooding dan ping flooding pada jaringan internet of things dengan pendekatan finite-state automata. Hasil pengujian menunjukkan bahwa pendekatan finite-state automata berhasil mendeteksi serangan synchronize flooding dan ping flooding pada jaringan internet of things, tetapi pencegahan serangan tidak secara signifikan mengurangi penggunaan prosesor dan memori. Serangan synchronize flooding menyebabkan delay saat mengaktifkan/menonaktifkan peralatan internet of things sedangkan serangan ping flooding menyebabkan error. Implementasi bash-iptables berhasil mengurangi serangan synchronize flooding dengan efisiensi waktu pencegahan sebesar 55,37% dan mengurangi serangan ping flooding sebesar 60% tetapi dengan waktu yang tidak signifikan.

show abstract

Section: Pendahuluanunclassified

Deteksi Serangan Denial of Service pada Internet of Things Menggunakan Finite-State Automata

Antony

Gustriansyah

2021

matrik

View full text Add to dashboard Cite

show abstract

“…An incremental learning framework is proposed in [5], where the user physically guides the robot, creating a sequence of coherent states that capture the demonstrated configurations in a Robot State Automaton (RSA). While demonstrating, the user has to identify situations, in which the task splits into different possible skills.…”

Section: Related Workmentioning

confidence: 99%

“…While previously described methods [5] - [8] rely on the user to identify unintended or new situations, the approaches in [3], [4], [10] and [16] aim to automatically detect anomalies or task deficiencies. Maeda et al [3] propose a method based on Gaussian Processes to quantify the generalization capability of an extrapolated trajectory for an unseen situation.…”

Section: Related Workmentioning

confidence: 99%

“…Compared to SBP, the decision state is explicitly programmed by actively querying the user instead of allowing arbitrary switching states, which do not guarantee a successful transition. User-Triggered Incremental Programming (UIP) is inspired by the framework presented in [5], where similar to CIP, a task-representing graph is incrementally constructed in a combined teaching and execution phase. The difference between these methods is, that the teacher has to detect anomalies with UIP during execution of the task and needs to decide if and when a new skill demonstration is needed.…”

Section: Gui On a Tabletmentioning

confidence: 99%

“…Two key questions of recent research on active learning [3] [4] are when to demonstrate additional behavior and on what regions of the input space to focus on with these demonstrations. While other PbD approaches rely on the user to monitor the task reproduction in order to identify new situations and task deficiencies [5]- [8], our proposed active learning framework automatically detects anomalies C. Willibald, T. Eiband Interactive PbD framework for programming of conditions, represented as decision states (DS) of a task-representing graph. In this example, a sensed contact force triggers a decision to execute either skill s 1A or s 2 .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Collaborative Programming of Conditional Robot Tasks

Willibald

Eiband

Lee

2020

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Conventional robot programming methods are not suited for non-experts to intuitively teach robots new tasks. For this reason, the potential of collaborative robots for production cannot yet be fully exploited. In this work, we propose an active learning framework, in which the robot and the user collaborate to incrementally program a complex task. Starting with a basic model, the robot's task knowledge can be extended over time if new situations require additional skills. An on-line anomaly detection algorithm therefore automatically identifies new situations during task execution by monitoring the deviation between measured-and commanded sensor values. The robot then triggers a teaching phase, in which the user decides to either refine an existing skill or demonstrate a new skill. The different skills of a task are encoded in separate probabilistic models and structured in a high-level graph, guaranteeing robust execution and successful transition between skills. In the experiments, our approach is compared to two state-of-the-art Programming by Demonstration frameworks on a real system. Increased intuitiveness and task performance of the method can be shown, allowing shop-floor workers to program industrial tasks with our framework.

show abstract

Extended State Automata for Intuitive Robot Programming

Sauer

Henrich

2021

Advances in Service and Industrial Robotics

View full text Add to dashboard Cite

Towards Intuitive Robot Programming Using Finite State Automata

Cited by 6 publications

References 21 publications

Deteksi Serangan Denial of Service pada Internet of Things Menggunakan Finite-State Automata

Deteksi Serangan Denial of Service pada Internet of Things Menggunakan Finite-State Automata

Collaborative Programming of Conditional Robot Tasks

Extended State Automata for Intuitive Robot Programming

Contact Info

Product

Resources

About