AKAbderrahmane Kheddar

Abderrahmane Kheddar

*This is an algorithmically generated author record based on publicly available information.

Abderrahmane Kheddar has a total of 215 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Normal and shear forces measurements at the interface of the skin–knee distraction orthosis during squatting: A feasibility study

    by Léa Boillereaux, Youcan Yan, Franck Jourdan, Abderrahmane Kheddar, Simon Le Floc’H

  • Humanoid Locomotion and Manipulation: Current Progress and Challenges in Control, Planning, and Learning

    by Zhaoyuan Gu, Junheng Li, Wenlan Shen, Wenhao Yu, Zhaoming Xie, Stephen McCrory, Xianyi Cheng, Abdulaziz Shamsah, Robert Griffin, C. Karen Liu, et al.

    Humanoid robots hold great potential to perform various human-level skills, involving unified locomotion and manipulation in real-world settings. Driven by advances in machine learning and the strength of existing model-based approaches, these capabilities have progressed rapidly, but often separately. This survey offers a comprehensive overview of the state-of-the-art in humanoid locomotion and manipulation, with a focus on control, planning, and learning methods. We first review the model-based methods that have been the backbone of humanoid robotics for the past three decades. We discuss contact planning, motion planning, and whole-body control, highlighting the tradeoffs between model fidelity and computational efficiency. Then, the focus is shifted to examine emerging learning-based methods, with an emphasis on reinforcement and imitation learning that enhance the robustness and versatility of loco-manipulation skills. Furthermore, we assess the potential of integrating foundation models with humanoid embodiments to enable the development of generalist humanoid agents. This survey also highlights the emerging role of tactile sensing, particularly whole-body tactile feedback, as a crucial modality for handling contact-rich interactions. Finally, we compare the strengths and limitations of model-based and learning-based paradigms from multiple perspectives, such as robustness, computational efficiency, versatility, and generalizability, and suggest potential solutions to existing challenges.


  • Impact-Aware Dual-Arm Manipulation: A Framework for Fast Package Handling

    by James Hermus, Michael Bombile, Jari J. van Steen, Elise Jeandupeux, Ahmed Zermane, Alessandro Melone, Mario Troebinger, Abdeldjallil Naceri, Claude Lacoursière, Stijn de Looijer, et al.

    This article presents an impact-aware manipulation framework and its application to logistics, where the challenges related to the booming of e-commerce have increased the need for faster and more flexible package handling solutions. Particularly, the proposed impact-aware framework addresses the problem of swiftly grabbing and placing objects in depalletizing tasks with dual-arm robotic systems. Impact-aware robotics leverages intentional collisions to achieve dynamic interactions and thus has the potential to be faster and more energy efficient than the state of the art based on quasi-static interactions with objects or environments. The generation of desired impacts (contacts at a nonzero relative speed), generally avoided in classical robotics, brings multiple challenges encompassing the generation of robust motions, managing the impact with the object, dealing with the physical constraints of the robotic systems, contact state sensing, and simulation of contact behavior. To tackle these challenges, we developed, within the European Union (EU)-funded project Impact-Aware Manipulation (I.AM.), impact-aware technologies that yield an integrated impact-aware solution. The proposed framework exploits nonsmooth mechanics to provide robot‒object‒environment impact models; it uses dynamical systems (DSs) to generate nominal and contingency motions with intentional impacts; it leverages quadratic programming (QP)-based control to provide motion execution with the ability to enforce hardware and safety constraints; it employs internal state sensing that does not require an external force transducer; and, finally, it develops an impact simulation environment that can handle batch simulations. This article highlights the benefits of the proposed approach in terms of speed (a 29% decrease in average task time) and energy efficiency (a 35% decrease) through a systematic comparison between classical grabbing and impact-aware swift grabbing and tossing. In summary, our article underscores the transformative potential of impact-aware technologies in revolutionizing robotic logistics operations. An accompanying video is available at https://youtu.be/0Tv-MxO0rG0.

  • Robust Bipedal Walking With Closed-Loop MPC: Adios Stabilizers

    by Antonin Dallard, Mehdi Benallegue, Nicola Scianca, Fumio Kanehiro, Abderrahmane Kheddar

    We propose a novel walking control scheme based on the dynamics of the Linear Inverted Pendulum (LIP) model. The pattern generation incorporates a model of contact forces, enabling closed-loop control of the humanoid robot's state, including the Center of Mass (CoM) position, velocity, and Zero Moment Point (ZMP). No additional control policies are required to maintain static and dynamic balance. Our approach also includes dynamic re-planning of step locations and timings, thus preserving the LIP's boundedness condition. We validated this controller on five different humanoid robots, testing its robustness through various disturbances, including sudden pushes during walking and static phases. Additionally, our controller demonstrated effective locomotion over uneven and compliant terrain. Both simulation and experimental results confirm the effectiveness and robustness of this controller.


  • Open Access

    Humanoid Loco-manipulation Planning based on Graph Search and Reachability Maps

    by Masaki Murooka, Iori Kumagai, Mitsuharu Morisawa, Fumio Kanehiro, Abderrahmane Kheddar

    In this letter, we propose an efficient and highly versatile loco-manipulation planning for humanoid robots. Loco-manipulation planning is a key technological brick enabling humanoid robots to autonomously perform object transportation by manipulating them. We formulate planning of the alternation and sequencing of footsteps and grasps as a graph search problem with a new transition model that allows for a flexible representation of loco-manipulation. Our transition model is quickly evaluated by relocating and switching the reachability maps depending on the motion of both the robot and object. We evaluate our approach by applying it to loco-manipulation use-cases, such as a bobbin rolling operation with regrasping, where the motion is automatically planned by our framework.

  • A Distraction Knee-Brace and a Robotic Testbed for Tibiofemoral Load Reduction During Squatting

    by Léa Boillereaux, Simon Le Floc’h, Franck Jourdan, Gille Camp, Arnaud Tanguy, Abderrahmane Kheddar

    We design and evaluate a new knee distraction unloader brace. The proposed device conforms to the nonlinear behavior of the tibiofemoral contact force during squat motions, by means of patient-custom cams. Using pneumatic cylinders as springs, the unloading assistance provided by the brace is tailored to the patient’s pathology and adjusted during the rehabilitation process. To assess the performance of our orthosis, various tests are conducted to evaluate its efficiency in terms of tibiofemoral contact load reduction. For this purpose, a robotic test-bench, equipped with a robotic arm, emulates upper leg motion under applied forces (hybrid force-motion control). A pseudo-leg is attached to the robot end-effector, and the orthosis is mounted onto it. The test bench is instrumented with two six degrees of freedom force-torque sensors. Using these force sensors as ground truth, tibiofemoral contact force measurements are obtained with and without our orthosis and compared. A pair of cams is fabricated based on data from a patient whose information is retrieved from the Orthoload database. Experimental results demonstrate a contact force reduction of up to 100 force range corresponding to the robot’s maximum capacity.


  • Fast Autolearning for Multimodal Walking in Humanoid Robots With Variability of Experience

    by Nícolas F. Figueroa, Julio C. Tafur, Abderrahmane Kheddar

    Recent advancements in reinforcement learning (RL) and humanoid robotics are rapidly addressing the challenge of adapting to complex, dynamic environments in real time. This letter introduces a novel approach that integrates two key concepts: experience variability (a criterion for detecting changes in loco-manipulation) and experience accumulation (an efficient method for storing acquired experiences based on a selection criterion). These elements are incorporated into the development of RL agents and humanoid robots, with an emphasis on stability. This focus enhances adaptability and efficiency in unpredictable environments. Our approach enables more sophisticated modeling of such environments, significantly improving the system's ability to adapt to real-world complexities. By combining this method with advanced RL techniques, such as Proximal Policy Optimization (PPO) and Model-Agnostic Meta-Learning (MAML), and incorporating self-learning driven by stability, we improve the system's generalization capabilities. This facilitates rapid learning from novel and previously unseen scenarios. We validate our algorithm through both simulations and real-world experiments on the HRP-4 humanoid robot, utilizing an intrinsically stable model predictive controller.


  • Humanoid Robot RHP Friends: Seamless Combination of Autonomous and Teleoperated Tasks in a Nursing Context

    by Mehdi Benallegue, Guillaume Lorthioir, Antonin Dallard, Rafael Cisneros-Limón, Iori Kumagai, Mitsuharu Morisawa, Hiroshi Kaminaga, Masaki Murooka, Antoine Andre, Pierre Gergondet, et al.

    This article describes RHP Friends, a social humanoid robot developed to enable assistive robotic deployments in human-coexisting environments. As a use case application, we present its potential use in nursing by extending its capabilities to operate devices and tools according to the task and by enabling remote assistance operations. To meet a wide variety of tasks and situations in environments designed by and for humans, we develop a system that seamlessly integrates the slim and lightweight robot and several technologies: locomanipulation, multicontact motion, teleoperation, and object detection and tracking. We demonstrate the system’s usage in a nursing application. The robot efficiently performs the daily task of patient transfer and a nonroutine task, represented by a request to operate a circuit breaker. This demonstration, held at the 2023 International Robot Exhibition (IREX), was conducted three times a day over three days.


  • Humanoid-Human Sit-to-Stand-to-Sit Assistance

    by Hugo Lefèvre, Tomohiro Chaki, Tomohiro Kawakami, Arnaud Tanguy, Takahide Yoshiike, Abderrahmane Kheddar

    Standing and sitting are basic tasks that become increasingly difficult with age or frailty. Assisting these movements using humanoid robots is a complex challenge, particularly in determining where and how much force the robot should apply to effectively support the human's dynamic motions. In this letter, we propose a method to compute assistive forces directly from the human's dynamic balance, using criteria typically employed in humanoid robots. Specifically, we map humanoid dynamic balance metrics onto human motion to calculate the forces required to stabilize the human's current posture. These forces are then applied at the appropriate locations on the human body by the humanoid. Our approach combines the variable height 3D divergent component of motion with gravito-inertial wrench cones to define a 3D balance region. Using centroidal feedback, we compute the required assistance force to maintain balance and distribute the resulting wrenches across the human's body using a humanoid robot dynamically balanced according to the same criteria. We demonstrate the effectiveness of this framework through both simulations and experiments, where a humanoid assists a person in sit-to-stand and stand-to-sit motions, with the person wearing an age-simulation suit to emulate frailty.


  • Structural Analysis and Design of Humanoid Arms From Human Arm Reachable Workspace

    by Xin Zhu, Haozhou Liu, Qingqing Li, Zhaoyang Cai, Xuechao Chen, Zhangguo Yu, Qiang Huang, Abderrahmane Kheddar

    Having a workspace (postural-reachable) for the humanoid arm that is similar to a human arm around the upper body is essential for effective operation in human-like environments. However, research in this area is scarce. This letter aims to investigate the optimal structural configuration of a humanoid arm in the workspace around the upper body (WAUB). For this purpose, we initiate by analyzing the reachability data of human arm in the WAUB and subsequently propose a design strategy that incorporates this human data into the humanoid arm design. The proposed strategy consists of two key components: a structural parameter optimization method based on the postural reachability of task points and a task point identification method tailored to the WAUB. The optimization process leverages the covariance matrix adaptation evolutionary strategy (CMA-ES) and integrates collision-free control into each optimization iteration for realistic arm motion. The task point identification involves defining an expected workspace derived from human data and selecting task points through analysis of the hard-to-reach areas. Humanoid upper body models are introduced considering the anthropomorphic contour of human body and humanoid shoulder features. Performance tests conducted on these models assess the effectiveness of optimization. The results can offer practical insights for humanoid arm design.