Teleoperation is a powerful method to generate reference motions and enable humanoid robots to perform a broad range of tasks. However, teleoperation becomes challenging when using hand contacts and non-coplanar surfaces, often leading to motor torque saturation or loss of stability through slipping. We propose a centroidal stability-based retargeting method that dynamically adjusts contact points and posture during teleoperation to enhance stability in these difficult scenarios. Central to our approach is an efficient analytical calculation of the stability margin gradient. This gradient is used to identify scenarios for which stability is highly sensitive to teleoperation setpoints and inform the local adjustment of these setpoints. We validate the framework in simulation and hardware by teleoperating manipulation tasks on a humanoid, demonstrating increased stability margins. We also demonstrate empirically that higher stability margins correlate with improved impulse resilience and joint torque margin.

Neural Information Processing Systems http://nips.cc/

High-mix low-volume (HMLV) industrial assembly, common in small and medium-sized enterprises (SMEs), requires the same precision, safety, and reliability as high-volume automation while remaining flexible to product variation and environmental uncertainty. Current robotic systems struggle to meet these demands. Manual programming is brittle and costly to adapt, while learning-based methods suffer from poor sample efficiency and unsafe exploration in contact-rich tasks. To address this, we present SHaRe-RL, a reinforcement learning framework that leverages multiple sources of prior knowledge. By (i) structuring skills into manipulation primitives, (ii) incorporating human demonstrations and online corrections, and (iii) bounding interaction forces with per-axis compliance, SHaRe-RL enables efficient and safe online learning for long-horizon, contact-rich industrial assembly tasks. Experiments on the insertion of industrial Harting connector modules with 0.2-0.4 mm clearance demonstrate that SHaRe-RL achieves reliable performance within practical time budgets. Our results show that process expertise, without requiring robotics or RL knowledge, can meaningfully contribute to learning, enabling safer, more robust, and more economically viable deployment of RL for industrial assembly.

This paper presents a reinforcement learning-based quadrotor navigation method that leverages efficient differentiable simulation, novel loss functions, and privileged information to navigate around large obstacles. Prior learning-based methods perform well in scenes that exhibit narrow obstacles, but struggle when the goal location is blocked by large walls or terrain. In contrast, the proposed method utilizes time-of-arrival (ToA) maps as privileged information and a yaw alignment loss to guide the robot around large obstacles. The policy is evaluated in photo-realistic simulation environments containing large obstacles, sharp corners, and dead-ends. Our approach achieves an 86% success rate and outperforms baseline strategies by 34%. We deploy the policy onboard a custom quadrotor in outdoor cluttered environments both during the day and night. The policy is validated across 20 flights, covering 589 meters without collisions at speeds up to 4 m/s.

Abstract--This paper explores the application of variational quantum circuits (VQCs) for solving offline contextual bandit problems in industrial optimization tasks. Using the Industrial Benchmark (IB) environment, we evaluate the performance of quantum regression models against classical models. Our findings demonstrate that quantum models can effectively fit complex reward functions, identify optimal configurations via particle swarm optimization (PSO), and generalize well in noisy and sparse datasets. These results provide a proof of concept for utilizing VQCs in offline contextual bandit problems and highlight their potential in industrial optimization tasks. Contextual bandit algorithms have emerged as powerful tools for decision-making under uncertainty. Driven by the increasing demand for personalization and adaptive decision-making, contextual bandits have been widely adopted in various domains, including recommender systems [1], [2], online advertising [3], and healthcare [4], where decisions must be made based on contextual information to maximize user engagement, click-through rates, or patient outcomes. In industrial applications, where systems must be continuously tuned or "steered" for optimal performance, contextual bandits offer a powerful approach to optimizing system configurations. In these settings, decisions need to be made based on contextual information (e.g., current operational state or environmental conditions), and the overall objective is to maximize some notion of reward (e.g., production throughput, energy efficiency, or product quality).

Climate control is crucial for greenhouse production as it directly affects crop growth and resource use. Reinforcement learning (RL) has received increasing attention in this field, but still faces challenges, including limited training efficiency and high reliance on initial learning conditions. Interactive RL, which combines human (grower) input with the RL agent's learning, offers a potential solution to overcome these challenges. However, interactive RL has not yet been applied to greenhouse climate control and may face challenges related to imperfect inputs. Therefore, this paper aims to explore the possibility and performance of applying interactive RL with imperfect inputs into greenhouse climate control, by: (1) developing three representative interactive RL algorithms tailored for greenhouse climate control (reward shaping, policy shaping and control sharing); (2) analyzing how input characteristics are often contradicting, and how the trade-offs between them make grower's inputs difficult to perfect; (3) proposing a neural network-based approach to enhance the robustness of interactive RL agents under limited input availability; (4) conducting a comprehensive evaluation of the three interactive RL algorithms with imperfect inputs in a simulated greenhouse environment. The demonstration shows that interactive RL incorporating imperfect grower inputs has the potential to improve the performance of the RL agent. RL algorithms that influence action selection, such as policy shaping and control sharing, perform better when dealing with imperfect inputs, achieving 8.4% and 6.8% improvement in profit, respectively. In contrast, reward shaping, an algorithm that manipulates the reward function, is sensitive to imperfect inputs and leads to a 9.4% decrease in profit. This highlights the importance of selecting an appropriate mechanism when incorporating imperfect inputs.

This communication on collision avoidance with unexpected obstacles is motivated by some critical appraisals on reinforcement learning (RL) which "requires ridiculously large numbers of trials to learn any new task" (Yann LeCun). We use the classic Dubins' car in order to replace RL with flatness-based control, combined with the HEOL feedback setting, and the latest model-free predictive control approach. The two approaches lead to convincing computer experiments where the results with the model-based one are only slightly better. They exhibit a satisfactory robustness with respect to randomly generated mismatches/disturbances, which become excellent in the model-free case. Those properties would have been perhaps difficult to obtain with today's popular machine learning techniques in AI. Finally, we should emphasize that our two methods require a low computational burden.

MOMAV (Marco's Omnidirectional Micro Aerial Vehicle) is a multirotor drone that is fully actuated, meaning it can control its orientation independently of its position. MOMAV is also highly symmetrical, making its flight efficiency largely unaffected by its current orientation. These characteristics are achieved by a novel drone design where six rotor arms align with the vertices of an octahedron, and where each arm can actively rotate along its long axis. Various standout features of MOMAV are presented: The high flight efficiency compared to arm configuration of other fully-actuated drones, the design of an original rotating arm assembly featuring slip-rings used to enable continuous arm rotation, and a novel control allocation algorithm based on sequential quadratic programming (SQP) used to calculate throttle and arm-angle setpoints in flight. Flight tests have shown that MOMAV is able to achieve remarkably low mean position/orientation errors of 6.6mm, 2.1° (σ: 3.0mm, 1.0°) when sweeping position setpoints, and 11.8mm, 3.3° (σ: 8.6mm, 2.0°) when sweeping orientation setpoints.

Humanoid robots can support human workers in physically demanding environments by performing tasks that require whole-body coordination, such as lifting and transporting heavy objects.These tasks, which we refer to as Dynamic Mobile Manipulation (DMM), require the simultaneous control of locomotion, manipulation, and posture under dynamic interaction forces. This paper presents a teleoperation framework for DMM on a height-adjustable wheeled humanoid robot for carrying heavy payloads. A Human-Machine Interface (HMI) enables whole-body motion retargeting from the human pilot to the robot by capturing the motion of the human and applying haptic feedback. The pilot uses body motion to regulate robot posture and locomotion, while arm movements guide manipulation.Real time haptic feedback delivers end effector wrenches and balance related cues, closing the loop between human perception and robot environment interaction. We evaluate the different telelocomotion mappings that offer varying levels of balance assistance, allowing the pilot to either manually or automatically regulate the robot's lean in response to payload-induced disturbances. The system is validated in experiments involving dynamic lifting of barbells and boxes up to 2.5 kg (21% of robot mass), demonstrating coordinated whole-body control, height variation, and disturbance handling under pilot guidance. Video demo can be found at: https://youtu.be/jF270_bG1h8?feature=shared

Reinforcement learning (RL) has made significant strides in legged robot control, enabling locomotion across diverse terrains and complex loco-manipulation capabilities. However, the commonly used position or velocity tracking-based objectives are agnostic to forces experienced by the robot, leading to stiff and potentially dangerous behaviors and poor control during forceful interactions. To address this limitation, we present \emph{Force-Adaptive Control via Impedance Reference Tracking} (FACET). Inspired by impedance control, we use RL to train a control policy to imitate a virtual mass-spring-damper system, allowing fine-grained control under external forces by manipulating the virtual spring. In simulation, we demonstrate that our quadruped robot achieves improved robustness to large impulses (up to 200 Ns) and exhibits controllable compliance, achieving an 80% reduction in collision impulse. The policy is deployed to a physical robot to showcase both compliance and the ability to engage with large forces by kinesthetic control and pulling payloads up to 2/3 of its weight. Further extension to a legged loco-manipulator and a humanoid shows the applicability of our method to more complex settings to enable whole-body compliance control. Project Website: https://facet.pages.dev/