Institution profile

Robert Bosch GmbH

Industry researcheurope · de
Official website
Research library214linked papers
Opportunities0open roles
Selected work

Representative Papers

Bridging Language and Action: A Survey of Language-Conditioned Robot Manipulation

Dec 17, 2023

This work addresses the semantic gap between natural language instructions and robotic physical actions to enhance the naturalness and reliability of human-robot collaboration. We propose the first four-dimensional taxonomy for language-conditioned robotic manipulation—comprising reward shaping, policy learning, neurosymbolic AI, and foundation model–driven approaches—and systematically analyze their fundamental limitations in generalization and safety. Integrating large language models (LLMs), vision-language models (VLMs), neurosymbolic reasoning, and multimodal semantic parsing, we develop a unified analytical framework spanning semantic extraction, environmental assessment, and auxiliary task design. Our analysis rigorously characterizes the performance boundaries of each paradigm for the first time, establishing theoretical foundations and concrete technical pathways toward safe, generalizable, and interpretable language-driven robotic systems.

10 citationsRead paper

Deployment of Containerized Simulations in an API-Driven Distributed Infrastructure

Jun 12, 2025

To address the challenges of heterogeneity, fragmented resources, and inefficient collaboration in embedded-system virtual-prototype simulation tools, this paper proposes SUNRISE—a scalable infrastructure for distributed simulation. SUNRISE introduces the Simulation Adapter Abstraction Layer (SAAL), a novel abstraction enabling plug-and-play integration of seven major commercial and open-source simulators. It leverages lightweight containerization (Docker/Kubernetes) and a RESTful microservice architecture to dynamically orchestrate simulation tasks across decentralized computing resources. An open API gateway is designed to facilitate cross-organizational collaboration. Experimental evaluation demonstrates that SUNRISE reduces simulation-task deployment latency by 62%, improves cross-organizational collaboration efficiency by 3×, and achieves a 99.8% API call success rate.

2 citationsRead paper

Shape optimization of geometrically nonlinear modal coupling coefficients: an application to MEMS gyroscopes

Mar 26, 2024Scientific Reports

Geometric nonlinearity in MEMS gyroscopes induces detrimental three-wave modal coupling, degrading performance and limiting linearity. Method: This work proposes a node-level parametric shape optimization framework to precisely tailor specific nonlinear coupling coefficients. Leveraging finite-element-based geometrically nonlinear modeling, sensitivity analysis of coupling coefficients, and constrained optimization algorithms, the method operates under manufacturability and operational constraints. Contribution/Results: It achieves, for the first time, targeted modulation of individual coupling coefficients across three to four orders of magnitude. The resulting topologies defy conventional design intuition, either significantly suppressing spurious nonlinearities or deliberately enhancing desired nonlinear functionalities. The approach provides a customizable, experimentally verifiable theoretical and technical pathway for designing high-linearity industrial gyroscopes and developing novel nonlinear MEMS devices.

2 citationsRead paper

Shape optimization of eigenfrequencies in MEMS gyroscopes

Feb 08, 2024Structural And Multidisciplinary Optimization

MEMS gyroscope resonator design suffers from heavy reliance on empirical knowledge, low optimization efficiency, and difficulty in simultaneously suppressing parasitic modes and ensuring manufacturability. Method: This paper proposes a node-level parametric shape optimization framework that integrates finite-element-based coordinate parameterization, analytical gradient derivation for eigenfrequencies and fabrication constraints, and gradient descent optimization. Contribution/Results: The method enables precise control of drive-mode frequency splitting and effective suppression of the first three harmonic-order parasitic modes. It automatically discovers non-intuitive, asymmetric geometries beyond human intuition, significantly expanding the feasible design space. The optimized designs exhibit high robustness and process compatibility, and the framework demonstrates generalizability across multiple MEMS resonator topologies.

2 citationsRead paper
Recent publications

Latest Papers