Search

The real-world application of small drones is mostly hampered by energy limitations. Neuromorphic computing promises extremely energy-efficient AI for autonomous flight, but is still challenging to train and deploy on real robots. In order to reap the maximal benefits from neuromorphic computing, it is desired to perform all autonomy functions end-to-end on a single neuromorphic chip, from low-level attitude control to high-level navigation. This research presents the first neuromorphic control system using a spiking neural network (SNN) to effectively map a drone's raw sensory input directly to motor commands. We apply this method to low-level attitude estimation and control for a quadrotor, deploying the SNN on a tiny Crazyflie. We propose a modular SNN, separately training and then merging estimation and control sub-networks. The SNN is trained with imitation learning, using a flight dataset of sensory-motor pairs. Post-training, the network is deployed on the Crazyflie, issuing control commands from sensor inputs at $500$Hz. Furthermore, for the training procedure we augmented training data by flying a controller with additional excitation and time-shifting the target data to enhance the predictive capabilities of the SNN. On the real drone the perception-to-control SNN tracks attitude commands with an average error of $3$ degrees, compared to $2.5$ degrees for the regular flight stack. We also show the benefits of the proposed learning modifications for reducing the average tracking error and reducing oscillations. Our work shows the feasibility of performing neuromorphic end-to-end control, laying the basis for highly energy-efficient and low-latency neuromorphic autopilots.

Relative localization (RL) is essential for the successful operation of micro air vehicle (MAV) swarms. Achieving accurate 3-D RL in infrastructure-free and GPS-denied environments with only distance information is a challenging problem that has not been satisfactorily solved. In this work, based on the range-based peer-to-peer RL using the ultra-wideband (UWB) ranging technique, we develop a novel UWB-based cooperative relative localization (CRL) solution that integrates the relative motion dynamics of each host-neighbor pair to build a unified dynamic model and takes the distances between the neighbors as \textit{bonus information}. Observability analysis using differential geometry shows that the proposed CRL scheme can expand the observable subspace compared to other alternatives using only direct distances between the host agent and its neighbors. In addition, we apply the kernel-induced extended Kalman filter (EKF) to the CRL state estimation problem with the novel-designed Logarithmic-Versoria (LV) kernel to tackle heavy-tailed UWB noise. Sufficient conditions for the convergence of the fixed-point iteration involved in the estimation algorithm are also derived. Comparative Monte Carlo simulations demonstrate that the proposed CRL scheme combined with the LV-kernel EKF significantly improves the estimation accuracy owing to its robustness against both measurement outliers and incorrect measurement covariance matrix initialization. Moreover, with the LV kernel, the estimation is still satisfactory when performing the fixed-point iteration only once for reduced computational complexity., Comment: 16 pages, 18 figures

Motion detection is a primary task required for robotic systems to perceive and navigate in their environment. Proposed in the literature bioinspired neuromorphic Time-Difference Encoder (TDE-2) combines event-based sensors and processors with spiking neural networks to provide real-time and energy-efficient motion detection through extracting temporal correlations between two points in space. However, on the algorithmic level, this design leads to loss of direction-selectivity of individual TDEs in textured environments. Here we propose an augmented 3-point TDE (TDE-3) with additional inhibitory input that makes TDE-3 direction-selectivity robust in textured environments. We developed a procedure to train the new TDE-3 using backpropagation through time and surrogate gradients to linearly map input velocities into an output spike count or an Inter-Spike Interval (ISI). Our work is the first instance of training a spiking neuron to have a specific ISI. Using synthetic data we compared training and inference with spike count and ISI with respect to changes in stimuli dynamic range, spatial frequency, and level of noise. ISI turns out to be more robust towards variation in spatial frequency, whereas the spike count is a more reliable training signal in the presence of noise. We performed the first in-depth quantitative investigation of optical flow coding with TDE and compared TDE-2 vs TDE-3 in terms of energy-efficiency and coding precision. Results show that on the network level both detectors show similar precision (20 degree angular error, 88% correlation with ground truth). Yet, due to the more robust direction-selectivity of individual TDEs, TDE-3 based network spike less and hence is more energy-efficient. Reported precision is on par with model-based methods but the spike-based processing of the TDEs provides allows more energy-efficient inference with neuromorphic hardware.

Many existing obstacle avoidance algorithms overlook the crucial balance between safety and agility, especially in environments of varying complexity. In our study, we introduce an obstacle avoidance pipeline based on reinforcement learning. This pipeline enables drones to adapt their flying speed according to the environmental complexity. Moreover, to improve the obstacle avoidance performance in cluttered environments, we propose a novel latent space. The latent space in this representation is explicitly trained to retain memory of previous depth map observations. Our findings confirm that varying speed leads to a superior balance of success rate and agility in cluttered environments. Additionally, our memory-augmented latent representation outperforms the latent representation commonly used in reinforcement learning. Finally, after minimal fine-tuning, we successfully deployed our network on a real drone for enhanced obstacle avoidance., Comment: 8 pages

Aggressive time-optimal control of quadcopters poses a significant challenge in the field of robotics. The state-of-the-art approach leverages reinforcement learning (RL) to train optimal neural policies. However, a critical hurdle is the sim-to-real gap, often addressed by employing a robust inner loop controller -an abstraction that, in theory, constrains the optimality of the trained controller, necessitating margins to counter potential disturbances. In contrast, our novel approach introduces high-speed quadcopter control using end-to-end RL (E2E) that gives direct motor commands. To bridge the reality gap, we incorporate a learned residual model and an adaptive method that can compensate for modeling errors in thrust and moments. We compare our E2E approach against a state-of-the-art network that commands thrust and body rates to an INDI inner loop controller, both in simulated and real-world flight. E2E showcases a significant 1.39-second advantage in simulation and a 0.17-second edge in real-world testing, highlighting end-to-end reinforcement learning's potential. The performance drop observed from simulation to reality shows potential for further improvement, including refining strategies to address the reality gap or exploring offline reinforcement learning with real flight data., Comment: 6 pages, 6 figures, 1 table

Overactuated Tilt Rotor Unmanned Aerial Vehicles are renowned for exceptional wind resistance and a broad operational range, which poses complex control challenges due to non-affine dynamics. Traditional solutions employ multi-state switched logic controllers for transitions. Our study introduces a novel unified incremental nonlinear controller for overactuated dual-axis tilting rotor quad-planes, seamlessly managing pitch, roll, and physical actuator commands. The control allocation problem is addressed using a SQP iterative optimization algorithm, well-suited for nonlinear actuator effectiveness in thrust vectoring vehicles. The controller design integrates desired roll and pitch angle inputs. These desired attitude angles are autonomously managed by the controller and then conveyed to the vehicle during slow airspeed phases, when the vehicle maintains its 6 DOF. We incorporate an AoA protection logic to prevent wing stall and a yaw rate reference model for coordinated turns. Flight tests confirm the controller's effectiveness in transitioning from hovering to forward flight, achieving desired vertical and lateral accelerations, and reverting to hovering.

Utilizing wind hovering techniques of soaring birds can save energy expenditure and improve the flight endurance of micro air vehicles (MAVs). Here, we present a novel method for fully autonomous orographic soaring without a priori knowledge of the wind field. Specifically, we devise an Incremental Nonlinear Dynamic Inversion (INDI) controller with control allocation, adapting it for autonomous soaring. This allows for both soaring and the use of the throttle if necessary, without changing any gain or parameter during the flight. Furthermore, we propose a simulated-annealing-based optimization method to search for soaring positions. This enables for the first time an MAV to autonomously find a feasible soaring position while minimizing throttle usage and other control efforts. Autonomous orographic soaring was performed in the wind tunnel. The wind speed and incline of a ramp were changed during the soaring flight. The MAV was able to perform autonomous orographic soaring for flight times of up to 30 minutes. The mean throttle usage was only 0.25% for the entire soaring flight, whereas normal powered flight requires 38%. Also, it was shown that the MAV can find a new soaring spot when the wind field changes during the flight., Comment: 8 pages, 11 figures, accepted to IROS 2023

We present a novel controller for fixed-wing UAVs that enables autonomous soaring in an orographic wind field, extending flight endurance. Our method identifies soaring regions and addresses position control challenges by introducing a target gradient line (TGL) on which the UAV achieves an equilibrium soaring position, where sink rate and updraft are balanced. Experimental testing validates the controller's effectiveness in maintaining autonomous soaring flight without using any thrust in a non-static wind field. We also demonstrate a single degree of control freedom in a soaring position through manipulation of the TGL., Comment: 6+1 pages, 9 figures, accepted to ICRA 2023

Spacecraft and drones aimed at exploring our solar system are designed to operate in conditions where the smart use of onboard resources is vital to the success or failure of the mission. Sensorimotor actions are thus often derived from high-level, quantifiable, optimality principles assigned to each task, utilizing consolidated tools in optimal control theory. The planned actions are derived on the ground and transferred onboard where controllers have the task of tracking the uploaded guidance profile. Here we argue that end-to-end neural guidance and control architectures (here called G&CNets) allow transferring onboard the burden of acting upon these optimality principles. In this way, the sensor information is transformed in real time into optimal plans thus increasing the mission autonomy and robustness. We discuss the main results obtained in training such neural architectures in simulation for interplanetary transfers, landings and close proximity operations, highlighting the successful learning of optimality principles by the neural model. We then suggest drone racing as an ideal gym environment to test these architectures on real robotic platforms, thus increasing confidence in their utilization on future space exploration missions. Drone racing shares with spacecraft missions both limited onboard computational capabilities and similar control structures induced from the optimality principle sought, but it also entails different levels of uncertainties and unmodelled effects. Furthermore, the success of G&CNets on extremely resource-restricted drones illustrates their potential to bring real-time optimal control within reach of a wider variety of robotic systems, both in space and on Earth.

Reaching fast and autonomous flight requires computationally efficient and robust algorithms. To this end, we train Guidance & Control Networks to approximate optimal control policies ranging from energy-optimal to time-optimal flight. We show that the policies become more difficult to learn the closer we get to the time-optimal 'bang-bang' control profile. We also assess the importance of knowing the maximum angular rotor velocity of the quadcopter and show that over- or underestimating this limit leads to less robust flight. We propose an algorithm to identify the current maximum angular rotor velocity onboard and a network that adapts its policy based on the identified limit. Finally, we extend previous work on Guidance & Control Networks by learning to take consecutive waypoints into account. We fly a 4x3m track in similar lap times as the differential-flatness-based minimum snap benchmark controller while benefiting from the flexibility that Guidance & Control Networks offer.

Developing optimal controllers for aggressive high-speed quadcopter flight poses significant challenges in robotics. Recent trends in the field involve utilizing neural network controllers trained through supervised or reinforcement learning. However, the sim-to-real transfer introduces a reality gap, requiring the use of robust inner loop controllers during real flights, which limits the network's control authority and flight performance. In this paper, we investigate for the first time, an end-to-end neural network controller, addressing the reality gap issue without being restricted by an inner-loop controller. The networks, referred to as G\&CNets, are trained to learn an energy-optimal policy mapping the quadcopter's state to rpm commands using an optimal trajectory dataset. In hover-to-hover flights, we identified the unmodeled moments as a significant contributor to the reality gap. To mitigate this, we propose an adaptive control strategy that works by learning from optimal trajectories of a system affected by constant external pitch, roll and yaw moments. In real test flights, this model mismatch is estimated onboard and fed to the network to obtain the optimal rpm command. We demonstrate the effectiveness of our method by performing energy-optimal hover-to-hover flights with and without moment feedback. Finally, we compare the adaptive controller to a state-of-the-art differential-flatness-based controller in a consecutive waypoint flight and demonstrate the advantages of our method in terms of energy optimality and robustness., Comment: 11 pages, 16 figures

Compelling evidence has been given for the high energy efficiency and update rates of neuromorphic processors, with performance beyond what standard Von Neumann architectures can achieve. Such promising features could be advantageous in critical embedded systems, especially in robotics. To date, the constraints inherent in robots (e.g., size and weight, battery autonomy, available sensors, computing resources, processing time, etc.), and particularly in aerial vehicles, severely hamper the performance of fully-autonomous on-board control, including sensor processing and state estimation. In this work, we propose a spiking neural network (SNN) capable of estimating the pitch and roll angles of a quadrotor in highly dynamic movements from 6-degree of freedom Inertial Measurement Unit (IMU) data. With only 150 neurons and a limited training dataset obtained using a quadrotor in a real world setup, the network shows competitive results as compared to state-of-the-art, non-neuromorphic attitude estimators. The proposed architecture was successfully tested on the Loihi neuromorphic processor on-board a quadrotor to estimate the attitude when flying. Our results show the robustness of neuromorphic attitude estimation and pave the way towards energy-efficient, fully autonomous control of quadrotors with dedicated neuromorphic computing systems.

Neuromorphic processing promises high energy efficiency and rapid response rates, making it an ideal candidate for achieving autonomous flight of resource-constrained robots. It will be especially beneficial for complex neural networks as are involved in high-level visual perception. However, fully neuromorphic solutions will also need to tackle low-level control tasks. Remarkably, it is currently still challenging to replicate even basic low-level controllers such as proportional-integral-derivative (PID) controllers. Specifically, it is difficult to incorporate the integral and derivative parts. To address this problem, we propose a neuromorphic controller that incorporates proportional, integral, and derivative pathways during learning. Our approach includes a novel input threshold adaptation mechanism for the integral pathway. This Input-Weighted Threshold Adaptation (IWTA) introduces an additional weight per synaptic connection, which is used to adapt the threshold of the post-synaptic neuron. We tackle the derivative term by employing neurons with different time constants. We first analyze the performance and limits of the proposed mechanisms and then put our controller to the test by implementing it on a microcontroller connected to the open-source tiny Crazyflie quadrotor, replacing the innermost rate controller. We demonstrate the stability of our bio-inspired algorithm with flights in the presence of disturbances. The current work represents a substantial step towards controlling highly dynamic systems with neuromorphic algorithms, thus advancing neuromorphic processing and robotics. In addition, integration is an important part of any temporal task, so the proposed Input-Weighted Threshold Adaptation (IWTA) mechanism may have implications well beyond control tasks.

Event cameras have recently gained significant traction since they open up new avenues for low-latency and low-power solutions to complex computer vision problems. To unlock these solutions, it is necessary to develop algorithms that can leverage the unique nature of event data. However, the current state-of-the-art is still highly influenced by the frame-based literature, and usually fails to deliver on these promises. In this work, we take this into consideration and propose a novel self-supervised learning pipeline for the sequential estimation of event-based optical flow that allows for the scaling of the models to high inference frequencies. At its core, we have a continuously-running stateful neural model that is trained using a novel formulation of contrast maximization that makes it robust to nonlinearities and varying statistics in the input events. Results across multiple datasets confirm the effectiveness of our method, which establishes a new state of the art in terms of accuracy for approaches trained or optimized without ground truth., Comment: ICCV 2023. 15 pages, 12 figures, 7 tables

Obstacle avoidance is an essential topic in the field of autonomous drone research. When choosing an avoidance algorithm, many different options are available, each with their advantages and disadvantages. As there is currently no consensus on testing methods, it is quite challenging to compare the performance between algorithms. In this paper, we propose AvoidBench, a benchmarking suite which can evaluate the performance of vision-based obstacle avoidance algorithms by subjecting them to a series of tasks. Thanks to the high fidelity of multi-rotors dynamics from RotorS and virtual scenes of Unity3D, AvoidBench can realize realistic simulated flight experiments. Compared to current drone simulators, we propose and implement both performance and environment metrics to reveal the suitability of obstacle avoidance algorithms for environments of different complexity. To illustrate AvoidBench's usage, we compare three algorithms: Ego-planner, MBPlanner, and Agile-autonomy. The trends observed are validated with real-world obstacle avoidance experiments.

Inspired by frame-based methods, state-of-the-art event-based optical flow networks rely on the explicit construction of correlation volumes, which are expensive to compute and store, rendering them unsuitable for robotic applications with limited compute and energy budget. Moreover, correlation volumes scale poorly with resolution, prohibiting them from estimating high-resolution flow. We observe that the spatiotemporally continuous traces of events provide a natural search direction for seeking pixel correspondences, obviating the need to rely on gradients of explicit correlation volumes as such search directions. We introduce IDNet (Iterative Deblurring Network), a lightweight yet high-performing event-based optical flow network directly estimating flow from event traces without using correlation volumes. We further propose two iterative update schemes: "ID" which iterates over the same batch of events, and "TID" which iterates over time with streaming events in an online fashion. Our top-performing ID model sets a new state of the art on DSEC benchmark. Meanwhile, the base ID model is competitive with prior arts while using 80% fewer parameters, consuming 20x less memory footprint and running 40% faster on the NVidia Jetson Xavier NX. Furthermore, the TID model is even more efficient offering an additional 5x faster inference speed and 8 ms ultra-low latency at the cost of only a 9% performance drop, making it the only model among current literature capable of real-time operation while maintaining decent performance., Comment: Accepted to IEEE International Conference on Robotics and Automation (ICRA'24), Yokohama, Japan, May 13-17, 2024. arXiv revision includes additional ablation studies results

Nano quadcopters are small, agile, and cheap platforms that are well suited for deployment in narrow, cluttered environments. Due to their limited payload, these vehicles are highly constrained in processing power, rendering conventional vision-based methods for safe and autonomous navigation incompatible. Recent machine learning developments promise high-performance perception at low latency, while dedicated edge computing hardware has the potential to augment the processing capabilities of these limited devices. In this work, we present NanoFlowNet, a lightweight convolutional neural network for real-time dense optical flow estimation on edge computing hardware. We draw inspiration from recent advances in semantic segmentation for the design of this network. Additionally, we guide the learning of optical flow using motion boundary ground truth data, which improves performance with no impact on latency. Validation results on the MPI-Sintel dataset show the high performance of the proposed network given its constrained architecture. Additionally, we successfully demonstrate the capabilities of NanoFlowNet by deploying it on the ultra-low power GAP8 microprocessor and by applying it to vision-based obstacle avoidance on board a Bitcraze Crazyflie, a 34 g nano quadcopter., Comment: 8 pages, 9 figures, 4 tables

Learning-based visual ego-motion estimation is promising yet not ready for navigating agile mobile robots in the real world. In this article, we propose CUAHN-VIO, a robust and efficient monocular visual-inertial odometry (VIO) designed for micro aerial vehicles (MAVs) equipped with a downward-facing camera. The vision frontend is a content-and-uncertainty-aware homography network (CUAHN) that is robust to non-homography image content and failure cases of network prediction. It not only predicts the homography transformation but also estimates its uncertainty. The training is self-supervised, so that it does not require ground truth that is often difficult to obtain. The network has good generalization that enables "plug-and-play" deployment in new environments without fine-tuning. A lightweight extended Kalman filter (EKF) serves as the VIO backend and utilizes the mean prediction and variance estimation from the network for visual measurement updates. CUAHN-VIO is evaluated on a high-speed public dataset and shows rivaling accuracy to state-of-the-art (SOTA) VIO approaches. Thanks to the robustness to motion blur, low network inference time (~23ms), and stable processing latency (~26ms), CUAHN-VIO successfully runs onboard an Nvidia Jetson TX2 embedded processor to navigate a fast autonomous MAV., Comment: 19 pages, 14 figures, 6 tables

Machine learning (ML) has become a pervasive tool across computing systems. An emerging application that stress-tests the challenges of ML system design is tiny robot learning, the deployment of ML on resource-constrained low-cost autonomous robots. Tiny robot learning lies at the intersection of embedded systems, robotics, and ML, compounding the challenges of these domains. Tiny robot learning is subject to challenges from size, weight, area, and power (SWAP) constraints; sensor, actuator, and compute hardware limitations; end-to-end system tradeoffs; and a large diversity of possible deployment scenarios. Tiny robot learning requires ML models to be designed with these challenges in mind, providing a crucible that reveals the necessity of holistic ML system design and automated end-to-end design tools for agile development. This paper gives a brief survey of the tiny robot learning space, elaborates on key challenges, and proposes promising opportunities for future work in ML system design., Comment: 4 pages, 3 figures, 1 table, in IEEE AICAS 2022

Enabling the capability of assessing risk and making risk-aware decisions is essential to applying reinforcement learning to safety-critical robots like drones. In this paper, we investigate a specific case where a nano quadcopter robot learns to navigate an apriori-unknown cluttered environment under partial observability. We present a distributional reinforcement learning framework to generate adaptive risk-tendency policies. Specifically, we propose to use lower tail conditional variance of the learnt return distribution as intrinsic uncertainty estimation, and use exponentially weighted average forecasting (EWAF) to adapt the risk-tendency in accordance with the estimated uncertainty. In simulation and real-world empirical results, we show that (1) the most effective risk-tendency vary across states, (2) the agent with adaptive risk-tendency achieves superior performance compared to risk-neutral policy or risk-averse policy baselines.

Nano quadcopters are ideal for gas source localization (GSL) as they are safe, agile and inexpensive. However, their extremely restricted sensors and computational resources make GSL a daunting challenge. In this work, we propose a novel bug algorithm named `Sniffy Bug', which allows a fully autonomous swarm of gas-seeking nano quadcopters to localize a gas source in an unknown, cluttered and GPS-denied environments. The computationally efficient, mapless algorithm foresees in the avoidance of obstacles and other swarm members, while pursuing desired waypoints. The waypoints are first set for exploration, and, when a single swarm member has sensed the gas, by a particle swarm optimization-based procedure. We evolve all the parameters of the bug (and PSO) algorithm, using our novel simulation pipeline, `AutoGDM'. It builds on and expands open source tools in order to enable fully automated end-to-end environment generation and gas dispersion modeling, allowing for learning in simulation. Flight tests show that Sniffy Bug with evolved parameters outperforms manually selected parameters in cluttered, real-world environments.

The rapid rise of accessibility of unmanned aerial vehicles or drones pose a threat to general security and confidentiality. Most of the commercially available or custom-built drones are multi-rotors and are comprised of multiple propellers. Since these propellers rotate at a high-speed, they are generally the fastest moving parts of an image and cannot be directly "seen" by a classical camera without severe motion blur. We utilize a class of sensors that are particularly suitable for such scenarios called event cameras, which have a high temporal resolution, low-latency, and high dynamic range. In this paper, we model the geometry of a propeller and use it to generate simulated events which are used to train a deep neural network called EVPropNet to detect propellers from the data of an event camera. EVPropNet directly transfers to the real world without any fine-tuning or retraining. We present two applications of our network: (a) tracking and following an unmarked drone and (b) landing on a near-hover drone. We successfully evaluate and demonstrate the proposed approach in many real-world experiments with different propeller shapes and sizes. Our network can detect propellers at a rate of 85.1% even when 60% of the propeller is occluded and can run at upto 35Hz on a 2W power budget. To our knowledge, this is the first deep learning-based solution for detecting propellers (to detect drones). Finally, our applications also show an impressive success rate of 92% and 90% for the tracking and landing tasks respectively., Comment: 11 pages, 10 figures, 6 tables. Accepted in Robotics: Science and Systems (RSS) 2021

Relative localization is an important ability for multiple robots to perform cooperative tasks in GPS-denied environment. This paper presents a novel autonomous positioning framework for monocular relative localization of multiple tiny flying robots. This approach does not require any groundtruth data from external systems or manual labelling. Instead, the proposed framework is able to label real-world images with 3D relative positions between robots based on another onboard relative estimation technology, using ultra-wide band (UWB). After training in this self-supervised manner, the proposed deep neural network (DNN) can predict relative positions of peer robots by purely using a monocular camera. This deep learning-based visual relative localization is scalable, distributed and autonomous. We also built an open-source and light-weight simulation pipeline by using Blender for 3D rendering, which allows synthetic image generation of other robots, and generalized training of the neural network. The proposed localization framework is tested on two real-world Crazyflie2 quadrotors by running the DNN on the onboard AIdeck (a tiny AI chip and monocular camera). All results demonstrate the effectiveness of the self-supervised multi-robot localization method., Comment: 6+1 pages, submitted to ICRA 2022

This paper proposes a model-based framework to automatically and efficiently design understandable and verifiable behaviors for swarms of robots. The framework is based on the automatic extraction of two distinct models: 1) a neural network model trained to estimate the relationship between the robots' sensor readings and the global performance of the swarm, and 2) a probabilistic state transition model that explicitly models the local state transitions (i.e., transitions in observations from the perspective of a single robot in the swarm) given a policy. The models can be trained from a data set of simulated runs featuring random policies. The first model is used to automatically extract a set of local states that are expected to maximize the global performance. These local states are referred to as desired local states. The second model is used to optimize a stochastic policy so as to increase the probability that the robots in the swarm observe one of the desired local states. Following these steps, the framework proposed in this paper can efficiently lead to effective controllers. This is tested on four case studies, featuring aggregation and foraging tasks. Importantly, thanks to the models, the framework allows us to understand and inspect a swarm's behavior. To this end, we propose verification checks to identify some potential issues that may prevent the swarm from achieving the desired global objective. In addition, we explore how the framework can be used in combination with a "standard" evolutionary robotics strategy (i.e., where performance is measured via simulation), or with online learning., Comment: 23 pages, 12 figures

Multi-robot systems can benefit from reinforcement learning (RL) algorithms that learn behaviours in a small number of trials, a property known as sample efficiency. This research thus investigates the use of learned world models to improve sample efficiency. We present a novel multi-agent model-based RL algorithm: Multi-Agent Model-Based Policy Optimization (MAMBPO), utilizing the Centralized Learning for Decentralized Execution (CLDE) framework. CLDE algorithms allow a group of agents to act in a fully decentralized manner after training. This is a desirable property for many systems comprising of multiple robots. MAMBPO uses a learned world model to improve sample efficiency compared to model-free Multi-Agent Soft Actor-Critic (MASAC). We demonstrate this on two simulated multi-robot tasks, where MAMBPO achieves a similar performance to MASAC, but requires far fewer samples to do so. Through this, we take an important step towards making real-life learning for multi-robot systems possible., Comment: Submitted to 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)

In the field of visual ego-motion estimation for Micro Air Vehicles (MAVs), fast maneuvers stay challenging mainly because of the big visual disparity and motion blur. In the pursuit of higher robustness, we study convolutional neural networks (CNNs) that predict the relative pose between subsequent images from a fast-moving monocular camera facing a planar scene. Aided by the Inertial Measurement Unit (IMU), we mainly focus on translational motion. The networks we study have similar small model sizes (around 1.35MB) and high inference speeds (around 10 milliseconds on a mobile GPU). Images for training and testing have realistic motion blur. Departing from a network framework that iteratively warps the first image to match the second with cascaded network blocks, we study different network architectures and training strategies. Simulated datasets and a self-collected MAV flight dataset are used for evaluation. The proposed setup shows better accuracy over existing networks and traditional feature-point-based methods during fast maneuvers. Moreover, self-supervised learning outperforms supervised learning. Videos and open-sourced code are available at https://github.com/tudelft/PoseNet_Planar, Comment: 10 pages, 10 figures, 7 tables. Accepted by ICRA 2021 (without the Appendix)

Lightweight aerial swarms have potential applications in scenarios where larger drones fail to operate efficiently. The primary foundation for lightweight aerial swarms is efficient relative localization, which enables cooperation and collision avoidance. Computing the real-time position is challenging due to extreme resource constraints. This paper presents an autonomous relative localization technique for lightweight aerial swarms without infrastructure by fusing ultra-wideband wireless distance measurements and the shared state information (e.g., velocity, yaw rate, height) from neighbors. This is the first fully autonomous, tiny, fast, and accurate relative localization scheme implemented on a team of 13 lightweight (33 grams) and resource-constrained (168MHz MCU with 192 KB memory) aerial vehicles. The proposed resource-constrained swarm ranging protocol is scalable, and a surprising theoretical result is discovered: the unobservability poses no issues because the state drift leads to control actions that make the state observable again. By experiment, less than 0.2m position error is achieved at the frequency of 16Hz for as many as 13 drones. The code is open-sourced, and the proposed technique is relevant not only for tiny drones but can be readily applied to many other resource-restricted robots. Video and code can be found at \textnormal{\url{https://shushuai3.github.io/autonomous-swarm/}}., Comment: Project link: https://shushuai3.github.io/autonomous-swarm/