Interactive robotic art systems integrate sensing, actuation, and control to create works that respond to participants’ presence and actions. Engineering perspectives often stress measurable performance—stability, fluency, robustness—while artistic perspectives foreground embodied experience, relational dynamics, and aesthetic intent, embracing ambiguity and contradiction. We present a three-axis framework combining systems-based analysis with a phenomenological account of participant experience: degrees of interaction (inputs/outputs), the interaction loop formed by the feedback control system and/or the participant, and the operating logic containing algorithmic features and parameters. Applying this framework to 34 examples, we map how agency is distributed, identify common sensing and actuation modalities, and examine how technical design shapes experience. The framework offers a shared vocabulary for roboticists and artists, enabling clearer comparison, communication, and collaboration. It positions robotic art as a site for meaning-making and as a testbed for novel interaction paradigms beyond efficiency-driven design.
This article traces a two-decade lineage of exoskeletal and wearable–robotic performances—Devolution, Inferno, xLimbs, Repeat, and Godspeed—to examine how technological augmentation reshapes movement, perception, and collective agency. The article articulates a nexus of sensorimotor mediation, instruction and participatory sensemaking, atmospheric and affective modulation, and collective coordination and distributed agency as a theoretical and analytical lens for understanding how these robotic performances reorganize the conditions of embodied action. The analysis suggests that cocreative symbiosis blends agency, intentionality, and expressivity, distributing them across human–machine assemblages rather than allowing either performer or machine to possess them alone. The article further considers the ethical, social, and cultural implications of such hybrid performances, arguing that artistic experimentation with exoskeletal systems provides methodological insight for the broader design of collaborative, assistive, and interactive robotics. Wearable–robotic performance is positioned as a vital research arena for rethinking embodiment, agency, and relationality in human–machine futures, demonstrating how artistic investigation can prototype new approaches to shared control, embodied instruction, and multiagent synchronization. In doing so, the article positions cocreative symbiosis as a transferable conceptual framework applicable across artistic, social, and technological domains, informing the future design of wearable, collaborative, and assistive robotic systems.
Earlier works with drawing robots were motivated by ideas of delegation and autonomy to create a distance between the artist’s intentions and the final mark. In contrast, we present Companion, an artistic apparatus integrating a drawing robot with multimodal large language models (LLMs) to reintroduce the artist’s presence through collaboration. Using in-context learning (ICL) and tool use for robot control, the system engages in bidirectional interaction via drawing and speech. Our goal is to develop an agent capable of pushing shared visual storytelling into unexpected aesthetic and narrative territories. Experiments demonstrate the system’s potential as a playful cocreative partner. To validate the artistic contribution, we employed the consensual assessment technique (CAT) with a panel of seven art world experts (curators, a collector, and an artist) familiar with the authors’ prior robotic works. The results confirm that the system produces artworks with a distinct aesthetic identity and professional exhibition merit.
We present the design and development of a robotic character performed live on stage in a theatrical play, with a focus on the novel control strategies used by a human puppeteer. The system enables real-time expressive behaviour through five core mapping strategies, including degree-of-freedom (DoF) consolidation, time-based intensity modulation, affective button mapping, motion scrubbing, and a global servo gain control. Beyond artistic applications, these techniques suggest new directions for intuitive and expressive teleoperation in robotics.
Transbronchial lung biopsy (TBLB) has increasingly been recognized as a clinically significant procedure for the early diagnosis and treatment of lung cancer. However, the complex anatomical anatomy and narrow bronchial pathways present substantial challenges for conventional bronchoscopy, demanding exceptional surgical expertise, skills, and meticulous precision. To address these limitations, robot-assisted bronchoscopic systems integrated with flexible continuum bending sections and advanced sensing technologies have been developed to enable dexterous access and ensure safe tissue interaction. This review systematically examines the recent advancements in robot-assisted bronchoscopic systems and classifies them into two primary categories based on actuation mechanisms: tendon-driven and magnetic-driven approaches. The innovative mechanical designs, intelligent sensing techniques, control strategies, clinical progress, and current limitations of these robotic systems have been critically analyzed and summarized. Furthermore, the evolutionary trends of flexible bronchoscopic robots suitable for TBLB have been outlined, and the remaining challenges and potential technical solutions
Humanoid robots are expected to operate in diverse and unpredictable environments, from cluttered indoor spaces to rough outdoor terrains. Achieving stable and agile locomotion under such conditions presents substantial challenges in motion planning and control. This survey article systematically reviews recent progress in planning and control strategies for humanoid robot locomotion in unstructured environments featuring unstructured terrains and external disturbances. We focus on existing methods in three main areas: planning, control, and unified end-to-end frameworks. Furthermore, as key components of a humanoid robot locomotion framework, perception and its integration with state estimation are briefly introduced. While classical optimization-based methods based on simplified or full-order models remain foundational, recent developments increasingly leverage learning-based policies and reactive adaptation to enhance robustness and generalization. We highlight the strengths and limitations of current approaches; identify open challenges in real-time reactivity, contact handling, and sim-to-real transfer; and outline potential future directions for integrating learning and optimization in scalable deployable locomotion systems.
The arts and entertainment robotics industry is expected to grow over the next decade as robotics and artificial intelligence technologies continue to advance. One particular subfield is choreorobotics, where robots are incorporated into live dance performances. This paper presents a novel approach to build choreographic collaborations among multiple humans and robots in a live, improvised performance. We describe the creative processes and the facilitating technologies that support real-time choreography of a human-robot team. Furthermore, we qualitatively assess the human-robot teaming system through interviews with dancers and choreographer. We also analyze qualitative data from the audience to assess their reception of the live performance.
As marine ecosystems face rapid and complex changes driven by climate change pressures and human activities, there is a growing need for intelligent and systematic research and observation. While current robotic systems serve as valuable complements to traditional oceanographic methods, they remain insufficient to meet the growing demands for comprehensive, multiscale, and real-time understanding of dynamic marine environments. Therefore, we introduce the Space-Land-Ocean Coordination (SLOC) robotics system as a unified framework that integrates aerial, terrestrial, surface, and underwater agents into a coordinated and cross-environment system. This system enables multiscale ecological intelligence, allowing robots to dynamically respond to complex coastal events, such as algal blooms, estuarine (river-sea surface) degradation, and benthic shifts. Unlike traditional single- platform missions, SLOC emphasizes shared spatial awareness, interoperable communication, and adaptive task reallocation across heterogeneous agents. We demonstrate the feasibility of this framework through recent advances in distributed autonomy and field-deployed marine platforms. We further outline key research directions, including underwater communication, distributed perception, cross-domain localization, edge decision making, and digital twin validation. Together, these efforts establish SLOC robotics as a foundation for next-generation ocean science that is more comprehensive, resilient, and responsive to global change.
Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.
Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.
Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.
Programming robots to perform manipulation tasks from natural language commands in complex environments remains challenging due to the gap between high-level semantic reasoning and low-level physical control. Existing approaches, ranging from end-to-end large language models (LLMs) and vision-language models (VLMs) to symbolic planning methods, often struggle with precise geometric reasoning. To address this limitation, we propose Planning with Object Keypoint-Axis Constraints for Robotic Manipulation (PORM), a hierarchical language-to-action framework that bridges semantics and geometry through a simulation-assisted object-centric digital twin. The digital twin generates task-specific multiview observations and integrates geometric correspondences with semantic cues to extract task-relevant keypoint-axis constraints. These constraints guide trajectory optimization based on real-time 6D pose estimation and are further refined through closed-loop visual feedback, enabling robust adaptation to object pose changes and external perturbations during manipulation. By combining symbolic reasoning with dense geometric information, PORM equips robots with stronger geometric awareness for tasks that require fine-grained spatial reasoning. Experiments on diverse manipulation tasks show that PORM outperforms recent baselines, including MOKA and CoPa, in success rate, generalization to novel scenarios, and robustness under disturbances.
As robotic technologies evolve, their potential in artistic creation becomes an increasingly relevant topic of inquiry. This study explores how professional abstract artists perceive and experience co-creative interactions with an autonomous painting robotic arm. Eight artists engaged in six painting sessions-three with a human partner, followed by three with a robot-and subsequently participated in semi-structured interviews analyzed through reflexive thematic analysis. Human-human interactions were described as intuitive, dialogic, and emotionally engaging, whereas human-robot sessions felt more playful and reflective, offering greater autonomy and prompting for novel strategies to overcome the system's limitations. This work offers one of the first empirical investigations into artists' lived experiences with a robot, highlighting the value of long-term engagement and a multidisciplinary approach to human-robot co-creation.
