Alireza Rastegarpanah

Introduction: Intent-driven robotic disassembly requires translating operator language and noisy RGB-D perception into grounded, precedence-consistent removal plans. This work extends a perception-grounded large language model (LLM) planning framework for two-arm electric vehicle (EV) battery disassembly and evaluates the pipeline’s effectiveness after replacing the LLM backbone. Methods: The system converts live RGB-D detections into structured scene text, rewrites coordinates into a frame-consistent LUZD representation, generates an ordered removal sequence, validates it with an LLM verifier, and applies a deterministic anti-hallucination filter that removes labels or coordinates not present in the perceived scene. The replacement LLM is first evaluated within the prior ensemble-based pipeline. The upgraded system then combines a single-checkpoint generator-verifier workflow, revised generator and verifier prompts, and an interactive, inspectable human-in-the-loop planning interface that displays intermediate outputs and final filtered plans. Results: On the same 200-scene, 600-intent benchmark used in earlier work, mean full-list correctness was 0.824 for the prior six-sample final pipeline, 0.896 when the replacement LLM was evaluated within that prior pipeline, 0.935 with the upgraded generator alone, and 0.959 with verification and filtering. The final upgraded configuration reduced the LLM-call count from seven to two. In a 12-participant within-subject pilot, mean time to accepted answer was lower on both tasks, the mean raw NASA-TLX score was lower, and all participants preferred the new interface. Discussion: These results suggest that structured scene text, clear prompts, verifier-based correction, deterministic grounding, and inspectable interfaces enhance human-in-the-loop disassembly planning.

Background: Recent advancements in enabling technologies, including artificial intelligence and telemedicine, alongside robust clinical study outcomes, have led to significant progress in upper limb and hand exoskeletons utilised for post-stroke rehabilitation. Objectives: This review aims to synthesize the recent scientific literature (2010–2025) on post-stroke upper-limb and hand exoskeletons, with particular attention to the sensing architectures—sensing modalities, signal processing, sensor fusion, and sensor-driven control—that integrate technical and biomedical domains to examine device architecture, clinical context, and outcome selection. Methods: A search of PubMed and Scopus was conducted on 10 November 2025, cross-checked against IEEE Xplore, Web of Science, Embase, and ACM Digital Library. We included studies evaluating wearable exoskeletons or robotic orthoses for the upper limb/hand in post-stroke rehabilitation. Two independent reviewers screened records and extracted data, with disagreements resolved by consensus. Data were synthesised using a predefined label-based taxonomy. The review protocol was not registered. Results: From 1889 identified records, 219 studies met the inclusion criteria. The synthesis reveals a transition from rigid, laboratory-centered systems to lighter, soft, and home-oriented solutions. Available evidence suggests potential impairment-level benefits, particularly for proximal motor control, but certainty remains limited due to heterogeneity, small samples, blinding limitations, inconsistent dosing, and limited long-term follow-up; gains in hand/finger dexterity appear even more variable. Discussion: While exoskeleton-assisted therapy appears associated with impairment-level gains, transfer to activities of daily living (ADLs) and real-world function remains inconsistently documented and insufficiently powered to support firm conclusions.

This paper addresses the problem of multi-robot coordination for complex manipulation task sequences. We present a vision-driven task-and-motion planning (TAMP) framework for a real dual-agent platform that integrates task decomposition and allocation with a learning-based planner. A GMM-informed RRT motion planner is coupled with a hybrid safety layer that combines predictive collision checking in a MoveIt/FCL digital twin with reactive avoidance and replanning. This integration is challenging as the system jointly satisfies task precedence, geometric feasibility, dynamic obstacle avoidance, and dual-arm coordination constraints. The framework operates in a closed loop by updating the remaining task sequence from repeated scene scans and completion-state tracking rather than executing a fixed open-loop plan. In EV battery disassembly experiments, compared with baseline RRTConnect under identical perception and task assignments, the proposed system reduces cumulative end-effector path length from 48.8 to 17.9 m ( − 63.3 % ) , improves makespan from 467.9 to 429.8 s ( − 8.1 % ) , and reduces swept volumes (R1: 0.583 → 0.139   m 3 , R2: 0.696 → 0.252   m 3 ) and overlap ( 0.064 → 0.034   m 3 ) . These results show that combining predictive planning and reactive collision avoidance in a real dual-arm disassembly scenario improves motion compactness, safety, and scalability to broader multi-robot sequential manipulation tasks.

Introduction: In this study, we address intent-driven task planning for complex multi-action manipulation sequences in heterogeneous multi-robot cells. Given a perception back-end that outputs a structured object-level scene description and a human operator’s natural-language intent, we generate a precedence-consistent object-level robot-action sequence, which can then be executed by passing each such action to a lower-level motion planning module. Methods: The pipeline integrates i. perception-to-text scene encoding, ii. an ensemble of large language models (LLMs) that generate candidate action sequences based on the operator’s intent, iii. an LLM-based verifier that enforces formatting and precedence constraints, and iv. a deterministic consistency filter that rejects hallucinated objects. The pipeline is evaluated on an example task in which two robot arms work collaboratively to dismantle an electric-vehicle (EV) battery for recycling applications. A variety of components must be grasped and removed in specific sequences, determined either by human instructions or by task-order feasibility decisions made by the autonomous system. Results: On 200 real scenes with 600 operator prompts across five component classes, we used metrics of full-sequence correctness and next-task correctness to evaluate and compare five LLM-based planners (including ablation analyses of pipeline components). We also evaluated the LLM-based human interface in terms of time to execution and NASA TLX using human participant experiments. On 200 real scenes and 600 prompts, full-sequence correctness improves from 0.761 (single LLM) to 0.824 (6-LLM + verifier + deterministic filter), and next-object correctness improves from 0.866 to 0.894. Discussion: Results in our case study indicate that our ensemble-with-verification approach reliably maps operator intent to safe multi-robot plans while maintaining low user effort.

Whereas reinforcement learning has been applied with success to a range of robotic control problems in complex, uncertain environments, reliance on extensive data - typically sourced from simulation environments - limits real-world deployment due to the domain gap between simulated and physical systems, coupled with limited real-world sample availability. We propose a novel method for sim-to-real transfer of reinforcement learning policies, based on a reinterpretation of neural style transfer from image processing to synthesise novel training data from unpaired unlabelled real world datasets. We employ a variational autoencoder to jointly learn self-supervised feature representations for style transfer and generate weakly paired source-target trajectories to improve physical realism of synthesised trajectories. We demonstrate the application of our approach based on the case study of robot cutting of unknown materials. Compared to baseline methods, including our previous work, CycleGAN, and conditional variational autoencoder-based time series translation, our approach achieves improved task completion time and behavioural stability with minimal real-world data. Our framework demonstrates robustness to geometric and material variation, and highlights the feasibility of policy adaptation in challenging contact-rich tasks where real-world reward information is unavailable.

Whereas reinforcement learning has been applied with success to a range of robotic control problems in complex, uncertain environments, reliance on extensive data - typically sourced from simulation environments - limits real-world deployment due to the domain gap between simulated and physical systems, coupled with limited real-world sample availability. We propose a novel method for sim-to-real transfer of reinforcement learning policies, based on a reinterpretation of neural style transfer from image processing to synthesise novel training data from unpaired unlabelled real world datasets. We employ a variational autoencoder to jointly learn self-supervised feature representations for style transfer and generate weakly paired source-target trajectories to improve physical realism of synthesised trajectories. We demonstrate the application of our approach based on the case study of robot cutting of unknown materials. Compared to baseline methods, including our previous work, CycleGAN, and conditional variational autoencoder-based time series translation, our approach achieves improved task completion time and behavioural stability with minimal real-world data. Our framework demonstrates robustness to geometric and material variation, and highlights the feasibility of policy adaptation in challenging contact-rich tasks where real-world reward information is unavailable.

This paper addresses the problem of planning complex manipulation tasks, in which multiple robots with different end-effectors and capabilities, informed by computer vision, must plan and execute concatenated sequences of actions on a variety of objects that can appear in arbitrary positions and configurations in unstructured scenes. We propose an intent-driven planning pipeline which can robustly construct such action sequences with varying degrees of supervisory input from a human using simple language instructions. The pipeline integrates: (i) perception-to-text scene encoding, (ii) an ensemble of large language models (LLMs) that generate candidate removal sequences based on the operator's intent, (iii) an LLM-based verifier that enforces formatting and precedence constraints, and (iv) a deterministic consistency filter that rejects hallucinated objects. The pipeline is evaluated on an example task in which two robot arms work collaboratively to dismantle an Electric Vehicle battery for recycling applications. A variety of components must be grasped and removed in specific sequences, determined by human instructions and/or by task-order feasibility decisions made by the autonomous system. On 200 real scenes with 600 operator prompts across five component classes, we used metrics of full-sequence correctness and next-task correctness to evaluate and compare five LLM-based planners (including ablation analyses of pipeline components). We also evaluated the LLM-based human interface in terms of time to execution and NASA TLX with human participant experiments. Results indicate that our ensemble-with-verification approach reliably maps operator intent to safe, executable multi-robot plans while maintaining low user effort.