Due to the wide spread of robotics technologies in everyday activities, from industrial automation to domestic assisted living applications, cutting-edge techniques such as deep reinforcement learning are intensively investigated with the aim to advance the technological robotics front. The mandatory limitation of power consumption remains an open challenge in contemporary robotics, especially in real-case applications. Spiking neural networks (SNN) constitute an ideal compromise as a strong computational tool with low-power capacities. This paper introduces a spiking neural network actor for a baseline robotic manipulation task using a dual-finger gripper. To achieve that, we used a hybrid deep deterministic policy gradient (DDPG) algorithm designed with a spiking actor and a deep critic network to train the robotic agent. Thus, the agent learns to obtain the optimal policies for the three main tasks of the robotic manipulation approach: target-object reach, grasp, and transfer. The proposed method has one of the main advantages that an SNN possesses, namely, its neuromorphic hardware implementation capacity that results in energy-efficient implementations. The latter accomplishment is highly demonstrated in the evaluation results of the SNN actor since the deep critic network was exploited only during training. Aiming to further display the capabilities of the introduced approach, we compare our model with the well-established DDPG algorithm.

/pdf/a-hybrid-spiking-neural-network-reinforcement-learning-agent-23hfl3ts.pdf

A Hybrid Spiking Neural Network Reinforcement Learning Agent for Energy-Efficient Object Manipulation

We present an environment for simulated experiments in field robotics, and especially in experiments on estimating the traversability of foliage and other objects that appear as obstacles but that can be overcome by the robot without circumventing them. The simulated environment is developed in the Unity real-time development platform, integrated with the ROS middleware. In the preliminary experiments presented here, we demonstrate that our environment is able to simulate the sensory input needed in order to train supervised traversability estimation models.

https://dl.acm.org/doi/pdf/10.1145/3453892.3462214

A Simulated Environment for Traversability Estimation Experiments in Field Robotics Applications

The article presents the application of a hyperspectral camera in mobile robot navigation. Hyperspectral cameras are imaging systems that can capture a wide range of electromagnetic spectra. This feature allows them to detect a broader range of colors and features than traditional cameras and to perceive the environment more accurately. Several surface types, such as mud, can be challenging to detect using an RGB camera. In our system, the hyperspectral camera is used for ground recognition (e.g., grass, bumpy road, asphalt). Traditional global path planning methods take the shortest path length as the optimization objective. We propose an improved A* algorithm to generate the collision-free path. Semantic information makes it possible to plan a feasible and safe path in a complex off-road environment, taking traveling time as the optimization objective. We presented the results of the experiments for data collected in a natural environment. An important novelty of this paper is using a modified nearest neighbor method for hyperspectral data analysis and then using the data for path planning tasks in the same work. Using the nearest neighbor method allows us to adjust the robotic system much faster than using neural networks. As our system is continuously evolving, we intend to examine the performance of the vehicle on various road surfaces, which is why we sought to create a classification system that does not require a prolonged learning process. In our paper, we aimed to demonstrate that the incorporation of a hyperspectral camera can not only enhance route planning but also aid in the determination of parameters such as speed and acceleration.

/pdf/hyperspectral-imaging-for-mobile-robot-navigation-2bq3kr5x.pdf

Hyperspectral Imaging for Mobile Robot Navigation

In this poster paper, we present a framework that blends self-supervised contrastive pre=training with semi-supervised learning using fine-tuning, as a means to perform successful image classification for traversability estimation purposes in an indoor environment scenario while addressing the small size of the collected dataset.

Towards A Traversability Estimation Framework for An Indoor Scenario Using Contrastive Learning

This paper presents a study of end-to-end methods for predicting autonomous vehicle navigation parameters. Image-based and Image & Lidar points-based end-to-end models have been trained under Nvidia learning architectures as well as Densenet-169, Resnet-152 and Inception-v4. Various learning parameters for autonomous vehicle navigation, input models and pre-processing data algorithms i.e. image cropping, noise removing, semantic segmentation for image data have been investigated and tested. The best ones, from the rigorous investigation, are selected for the main framework of the study. Results reveal that the Nvidia architecture trained Image & Lidar points-based method offers the better results accuracy rate-wise for steering angle and speed.

Predicting Autonomous Vehicle Navigation Parameters via Image and Image-and-Point Cloud Fusion-based End-to-End Methods

The ability to have unmanned ground vehicles navigate unmapped off-road terrain has high impact potential in application areas ranging from supply and logistics, to search and rescue, to planetary exploration. To achieve this, robots must be able to estimate the traversability of the terrain they are facing, in order to be able to plan a safe path through rugged terrain. In the work described here, we pursue the idea of fine-tuning a generic visual recognition network to our task and to new environments, but without requiring any manually labelled data. Instead, we present an autonomous data collection method that allows the robot to derive ground truth labels by attempting to traverse a scene and using localization to decide if the traversal was successful. We then present and experimentally evaluate two deep learning architectures that can be used to adapt a pre-trained network to a new environment. We prove that the networks successfully adapt to their new task and environment from a relatively small dataset.

Katerina Maria Oikonomou

Papers

Improving Traversability Estimation Through Autonomous Robot Experimentation.