Robust Offline Imitation Learning from Diverse Auxiliary Data

Offline imitation learning enables learning a policy solely from a set of expert demonstrations, without any environment interaction. To alleviate the issue of distribution shift arising due to the small amount of expert data, recent works incorporate large numbers of auxiliary demonstrations alongside the expert data. However, the performance of these approaches rely on assumptions about the quality and composition of the auxiliary data. However, they are rarely successful when those assumptions do not hold. To address this limitation, we propose Robust Offline Imitation from Diverse Auxiliary Data (ROIDA). ROIDA first identifies high-quality transitions from the entire auxiliary dataset using a learned reward function. These high-reward samples are combined with the expert demonstrations for weighted behavioral cloning. For lower-quality samples, ROIDA applies temporal difference learning to steer the policy towards high-reward states, improving long-term returns. This two-pronged approach enables our framework to effectively leverage both high and low-quality data without any assumptions. Extensive experiments validate that ROIDA achieves robust and consistent performance across multiple auxiliary datasets with diverse ratios of expert and non-expert demonstrations. ROIDA effectively leverages unlabeled auxiliary data, outperforming prior methods reliant on specific data assumptions.

Language-guided Robust Navigation for Mobile Robots in Dynamically-changing Environments

In this paper, we develop an embodied AI system for human-in-the-loop navigation with a wheeled mobile robot. We propose a direct yet effective method of monitoring the robot's current plan to detect changes in the environment that impact the intended trajectory of the robot significantly and then query a human for feedback. We also develop a means to parse human feedback expressed in natural language into local navigation waypoints and integrate it into a global planning system, by leveraging a map of semantic features and an aligned obstacle map. Extensive testing in simulation and physical hardware experiments with a resource-constrained wheeled robot tasked to navigate in a real-world environment validate the efficacy and robustness of our method. This work can support applications like precision agriculture and construction, where persistent monitoring of the environment provides a human with information about the environment state.

Hierarchical Tri-manual Planning for Vision-assisted Fruit Harvesting with Quadrupedal Robots

This paper addresses the challenge of developing a multi-arm quadrupedal robot capable of efficiently harvesting fruit in complex, natural environments. To overcome the inherent limitations of traditional bimanual manipulation, we introduce the first three-arm quadrupedal robot LocoHarv-3 and propose a novel hierarchical tri-manual planning approach, enabling automated fruit harvesting with collision-free trajectories. Our comprehensive semi-autonomous framework integrates teleoperation, supported by LiDAR-based odometry and mapping, with learning-based visual perception for accurate fruit detection and pose estimation. Validation is conducted through a series of controlled indoor experiments using motion capture and extensive field tests in natural settings. Results demonstrate a 90\% success rate in in-lab settings with a single attempt, and field trials further verify the system's robustness and efficiency in more challenging real-world environments.

Vision-based Xylem Wetness Classification in Stem Water Potential Determination

Water is often overused in irrigation, making efficient management of it crucial. Precision Agriculture emphasizes tools like stem water potential (SWP) analysis for better plant status determination. However, such tools often require labor-intensive in-situ sampling. Automation and machine learning can streamline this process and enhance outcomes. This work focused on automating stem detection and xylem wetness classification using the Scholander Pressure Chamber, a widely used but demanding method for SWP measurement. The aim was to refine stem detection and develop computer-vision-based methods to better classify water emergence at the xylem. To this end, we collected and manually annotated video data, applying vision- and learning-based methods for detection and classification. Additionally, we explored data augmentation and fine-tuned parameters to identify the most effective models. The identified best-performing models for stem detection and xylem wetness classification were evaluated end-to-end over 20 SWP measurements. Learning-based stem detection via YOLOv8n combined with ResNet50-based classification achieved a Top-1 accuracy of 80.98%, making it the best-performing approach for xylem wetness classification.

Vision-assisted Avocado Harvesting with Aerial Bimanual Manipulation

Robotic fruit harvesting holds potential in precision agriculture to improve harvesting efficiency. While ground mobile robots are mostly employed in fruit harvesting, certain crops, like avocado trees, cannot be harvested efficiently from the ground alone. This is because of unstructured ground and planting arrangement and high-to-reach fruits. In such cases, aerial robots integrated with manipulation capabilities can pave new ways in robotic harvesting. This paper outlines the design and implementation of a bimanual UAV that employs visual perception and learning to autonomously detect avocados, reach, and harvest them. The dual-arm system comprises a gripper and a fixer arm, to address a key challenge when harvesting avocados: once grasped, a rotational motion is the most efficient way to detach the avocado from the peduncle; however, the peduncle may store elastic energy preventing the avocado from being harvested. The fixer arm aims to stabilize the peduncle, allowing the gripper arm to harvest. The integrated visual perception process enables the detection of avocados and the determination of their pose; the latter is then used to determine target points for a bimanual manipulation planner. Several experiments are conducted to assess the efficacy of each component, and integrated experiments assess the effectiveness of the system.

Koopman Operators in Robot Learning

Koopman operator theory offers a rigorous treatment of dynamics and has been emerging as a powerful modeling and learning-based control method enabling significant advancements across various domains of robotics. Due to its ability to represent nonlinear dynamics as a linear operator, Koopman theory offers a fresh lens through which to understand and tackle the modeling and control of complex robotic systems. Moreover, it enables incremental updates and is computationally inexpensive making it particularly appealing for real-time applications and online active learning. This review comprehensively presents recent research results on advancing Koopman operator theory across diverse domains of robotics, encompassing aerial, legged, wheeled, underwater, soft, and manipulator robotics. Furthermore, it offers practical tutorials to help new users get started as well as a treatise of more advanced topics leading to an outlook on future directions and open research questions. Taken together, these provide insights into the potential evolution of Koopman theory as applied to the field of robotics.

Force Profiling of a Shoulder Bidirectional Fabric-based Pneumatic Actuator for a Pediatric Exosuit

This paper presents a comprehensive analysis of the contact force profile of a single-cell bidirectional soft pneumatic actuator, specifically designed to aid in the abduction and adduction of the shoulder for pediatric exosuits. The actuator was embedded in an infant-scale test rig featuring two degrees of freedom: an actuated revolute joint supporting shoulder abduction/adduction and a passive (but lockable) revolute joint supporting elbow flexion/extension. Integrated load cells and an encoder within the rig were used to measure the force applied by the actuator and the shoulder joint angle, respectively. The actuator's performance was evaluated under various anchoring points and elbow joint angles. Experimental results demonstrate that optimal performance, characterized by maximum range of motion and minimal force applied on the torso and upper arm, can be achieved when the actuator is anchored at two-thirds the length of the upper arm, with the elbow joint positioned at a 90-degree angle. The force versus pressure and joint angle graphs reveal nonlinear and hysteresis behaviors. The findings of this study yield insights about optimal anchoring points and elbow angles to minimize exerted forces without reducing the range of motion.

Adaptive Environment-Aware Robotic Arm Reaching Based on a Bio-Inspired Neurodynamical Computational Framework

Bio-inspired robotic systems are capable of adaptive learning, scalable control, and efficient information processing. Enabling real-time decision-making for such systems is critical to respond to dynamic changes in the environment. We focus on dynamic target tracking in open areas using a robotic six-degree-of-freedom manipulator with a bird-eye view camera for visual feedback, and by deploying the Neurodynamical Computational Framework (NeuCF). NeuCF is a recently developed bio-inspired model for target tracking based on Dynamic Neural Fields (DNFs) and Stochastic Optimal Control (SOC) theory. It has been trained for reaching actions on a planar surface toward localized visual beacons, and it can re-target or generate stop signals on the fly based on changes in the environment (e.g., a new target has emerged, or an existing one has been removed). We evaluated our system over various target-reaching scenarios. In all experiments, NeuCF had high end-effector positional accuracy, generated smooth trajectories, and provided reduced path lengths compared with a baseline cubic polynomial trajectory generator. In all, the developed system offers a robust and dynamic-aware robotic manipulation approach that affords real-time decision-making.

Design and Central Pattern Generator Control of a New Transformable Wheel-Legged Robot

This paper introduces a new wheel-legged robot and develops motion controllers based on central pattern generators (CPGs) for the robot to navigate over a range of terrains. A transformable leg-wheel design is considered and characterized in terms of key locomotion characteristics as a function of the design. Kinematic analysis is conducted based on a generalized four-bar mechanism driven by a coaxial hub arrangement. The analysis is used to inform the design of a central pattern generator to control the robot by mapping oscillator states to wheel-leg trajectories and implementing differential steering within the oscillator network. Three oscillator models are used as the basis of the CPGs, and their performance is compared over a range of inputs. The CPG-based controller is used to drive the developed robot prototype on level ground and over obstacles. Additional simulated tests are performed for uneven terrain negotiation and obstacle climbing. Results demonstrate the effectiveness of CPG control in transformable wheel-legged robots.

Design of an End-effector with Application to Avocado Harvesting

Robot-assisted fruit harvesting has been a critical research direction supporting sustainable crop production. One important determinant of system behavior and efficiency is the end-effector that comes in direct contact with the crop during harvesting and directly affects harvesting success. Harvesting avocados poses unique challenges not addressed by existing end-effectors (namely, they have uneven surfaces and irregular shapes grow on thick peduncles, and have a sturdy calyx attached). The work reported in this paper contributes a new end-effector design suitable for avocado picking. A rigid system design with a two-stage rotational motion is developed, to first grasp the avocado and then detach it from its peduncle. A force analysis is conducted to determine key design parameters. Preliminary experiments demonstrate the efficiency of the developed end-effector to pick and apply a moment to an avocado from a specific viewpoint (as compared to pulling it directly), and in-lab experiments show that the end-effector can grasp and retrieve avocados with a 100% success rate.