Benchmarking Reinforcement Learning Methods for Dexterous Robotic Manipulation with a Three-Fingered Gripper

Reinforcement Learning (RL) training is predominantly conducted in cost-effective and controlled simulation environments. However, the transfer of these trained models to real-world tasks often presents unavoidable challenges. This research explores the direct training of RL algorithms in controlled yet realistic real-world settings for the execution of dexterous manipulation. The benchmarking results of three RL algorithms trained on intricate in-hand manipulation tasks within practical real-world contexts are presented. Our study not only demonstrates the practicality of RL training in authentic real-world scenarios, facilitating direct real-world applications, but also provides insights into the associated challenges and considerations. Additionally, our experiences with the employed experimental methods are shared, with the aim of empowering and engaging fellow researchers and practitioners in this dynamic field of robotics.

Image-Based Deep Reinforcement Learning with Intrinsically Motivated Stimuli: On the Execution of Complex Robotic Tasks

Reinforcement Learning (RL) has been widely used to solve tasks where the environment consistently provides a dense reward value. However, in real-world scenarios, rewards can often be poorly defined or sparse. Auxiliary signals are indispensable for discovering efficient exploration strategies and aiding the learning process. In this work, inspired by intrinsic motivation theory, we postulate that the intrinsic stimuli of novelty and surprise can assist in improving exploration in complex, sparsely rewarded environments. We introduce a novel sample-efficient method able to learn directly from pixels, an image-based extension of TD3 with an autoencoder called \textit{NaSA-TD3}. The experiments demonstrate that NaSA-TD3 is easy to train and an efficient method for tackling complex continuous-control robotic tasks, both in simulated environments and real-world settings. NaSA-TD3 outperforms existing state-of-the-art RL image-based methods in terms of final performance without requiring pre-trained models or human demonstrations.

CTD4 - A Deep Continuous Distributional Actor-Critic Agent with a Kalman Fusion of Multiple Critics

Categorical Distributional Reinforcement Learning (CDRL) has demonstrated superior sample efficiency in learning complex tasks compared to conventional Reinforcement Learning (RL) approaches. However, the practical application of CDRL is encumbered by challenging projection steps, detailed parameter tuning, and domain knowledge. This paper addresses these challenges by introducing a pioneering Continuous Distributional Model-Free RL algorithm tailored for continuous action spaces. The proposed algorithm simplifies the implementation of distributional RL, adopting an actor-critic architecture wherein the critic outputs a continuous probability distribution. Additionally, we propose an ensemble of multiple critics fused through a Kalman fusion mechanism to mitigate overestimation bias. Through a series of experiments, we validate that our proposed method is easy to train and serves as a sample-efficient solution for executing complex continuous-control tasks.

Deep Reinforcement Learning for Local Path Following of an Autonomous Formula SAE Vehicle

With the continued introduction of driverless events to Formula:Society of Automotive Engineers (F:SAE) competitions around the world, teams are investigating all aspects of the autonomous vehicle stack. This paper presents the use of Deep Reinforcement Learning (DRL) and Inverse Reinforcement Learning (IRL) to map locally-observed cone positions to a desired steering angle for race track following. Two state-of-the-art algorithms not previously tested in this context: soft actor critic (SAC) and adversarial inverse reinforcement learning (AIRL), are used to train models in a representative simulation. Three novel reward functions for use by RL algorithms in an autonomous racing context are also discussed. Tests performed in simulation and the real world suggest that both algorithms can successfully train models for local path following. Suggestions for future work are presented to allow these models to scale to a full F:SAE vehicle.

Racing Towards Reinforcement Learning based control of an Autonomous Formula SAE Car

With the rising popularity of autonomous navigation research, Formula Student (FS) events are introducing a Driverless Vehicle (DV) category to their event list. This paper presents the initial investigation into utilising Deep Reinforcement Learning (RL) for end-to-end control of an autonomous FS race car for these competitions. We train two state-of-the-art RL algorithms in simulation on tracks analogous to the full-scale design on a Turtlebot2 platform. The results demonstrate that our approach can successfully learn to race in simulation and then transfer to a real-world racetrack on the physical platform. Finally, we provide insights into the limitations of the presented approach and guidance into the future directions for applying RL toward full-scale autonomous FS racing.

Seeing the Fruit for the Leaves: Robotically Mapping Apple Fruitlets in a Commercial Orchard

Aotearoa New Zealand has a strong and growing apple industry but struggles to access workers to complete skilled, seasonal tasks such as thinning. To ensure effective thinning and make informed decisions on a per-tree basis, it is crucial to accurately measure the crop load of individual apple trees. However, this task poses challenges due to the dense foliage that hides the fruitlets within the tree structure. In this paper, we introduce the vision system of an automated apple fruitlet thinning robot, developed to tackle the labor shortage issue. This paper presents the initial design, implementation,and evaluation specifics of the system. The platform straddles the 3.4 m tall 2D apple canopy structures to create an accurate map of the fruitlets on each tree. We show that this platform can measure the fruitlet load on an apple tree by scanning through both sides of the branch. The requirement of an overarching platform was justified since two-sided scans had a higher counting accuracy of 81.17 % than one-sided scans at 73.7 %. The system was also demonstrated to produce size estimates within 5.9% RMSE of their true size.

Visual based Tomato Size Measurement System for an Indoor Farming Environment

As technology progresses, smart automated systems will serve an increasingly important role in the agricultural industry. Current existing vision systems for yield estimation face difficulties in occlusion and scalability as they utilize a camera system that is large and expensive, which are unsuitable for orchard environments. To overcome these problems, this paper presents a size measurement method combining a machine learning model and depth images captured from three low cost RGBD cameras to detect and measure the height and width of tomatoes. The performance of the presented system is evaluated on a lab environment with real tomato fruits and fake leaves to simulate occlusion in the real farm environment. To improve accuracy by addressing fruit occlusion, our three-camera system was able to achieve a height measurement accuracy of 0.9114 and a width accuracy of 0.9443.

Look how they have grown: Non-destructive Leaf Detection and Size Estimation of Tomato Plants for 3D Growth Monitoring

Smart farming is a growing field as technology advances. Plant characteristics are crucial indicators for monitoring plant growth. Research has been done to estimate characteristics like leaf area index, leaf disease, and plant height. However, few methods have been applied to non-destructive measurements of leaf size. In this paper, an automated non-destructive imaged-based measuring system is presented, which uses 2D and 3D data obtained using a Zivid 3D camera, creating 3D virtual representations (digital twins) of the tomato plants. Leaves are detected from corresponding 2D RGB images and mapped to their 3D point cloud using the detected leaf masks, which then pass the leaf point cloud to the plane fitting algorithm to extract the leaf size to provide data for growth monitoring. The performance of the measurement platform has been measured through a comprehensive trial on real-world tomato plants with quantified performance metrics compared to ground truth measurements. Three tomato leaf and height datasets (including 50+ 3D point cloud files of tomato plants) were collected and open-sourced in this project. The proposed leaf size estimation method demonstrates an RMSE value of 4.47mm and an R^2 value of 0.87. The overall measurement system (leaf detection and size estimation algorithms combine) delivers an RMSE value of 8.13mm and an R^2 value of 0.899.

Seeing the Fruit for the Leaves: Towards Automated Apple Fruitlet Thinning

Following a global trend, the lack of reliable access to skilled labour is causing critical issues for the effective management of apple orchards. One of the primary challenges is maintaining skilled human operators capable of making precise fruitlet thinning decisions. Thinning requires accurately measuring the true crop load for individual apple trees to provide optimal thinning decisions on an individual basis. A challenging task due to the dense foliage obscuring the fruitlets within the tree structure. This paper presents the initial design, implementation, and evaluation details of the vision system for an automatic apple fruitlet thinning robot to meet this need. The platform consists of a UR5 robotic arm and stereo cameras which enable it to look around the leaves to map the precise number and size of the fruitlets on the apple branches. We show that this platform can measure the fruitlet load on the apple tree to with 84% accuracy in a real-world commercial apple orchard while being 87% precise.

Kiwifruit detection in challenging conditions

Accurate and reliable kiwifruit detection is one of the biggest challenges in developing a selective fruit harvesting robot. The vision system of an orchard robot faces difficulties such as dynamic lighting conditions and fruit occlusions. This paper presents a semantic segmentation approach with two novel image prepossessing techniques designed to detect kiwifruit under the harsh lighting conditions found in the canopy. The performance of the presented system is evaluated on a 3D real-world image set of kiwifruit under different lighting conditions (typical, glare, and overexposed). Alone the semantic segmentation approach achieves an F1_score of 0.82 on the typical lighting image set, but struggles with harsh lighting with an F1_score of 0.13. Utilising the prepossessing techniques the vision system under harsh lighting improves to an F1_score 0.42. To address the fruit occlusion challenge, the overall approach was found to be capable of detecting 87.0% of non-occluded and 30.0% of occluded kiwifruit across all lighting conditions.