This paper presents a novel approach for robust 3D tracking of multiple birds in an outdoor aviary using a multi-camera system. Our method addresses the challenges of visually similar birds and their rapid movements by leveraging environmental landmarks for enhanced feature matching and 3D reconstruction. In our approach, outliers are rejected based on their nearest landmark. This enables precise 3D-modeling and simultaneous tracking of multiple birds. By utilizing environmental context, our approach significantly improves the differentiation between visually similar birds, a key obstacle in existing tracking systems. Experimental results demonstrate the effectiveness of our method, showing a 20% elimination of outliers in the 3D reconstruction process, with a 97% accuracy in matching. This remarkable accuracy in 3D modeling translates to robust and reliable tracking of multiple birds, even in challenging outdoor conditions. Our work not only advances the field of computer vision but also provides a valuable tool for studying bird behavior and movement patterns in natural settings. We also provide a large annotated dataset of 80 birds residing in four enclosures for 20 hours of footage which provides a rich testbed for researchers in computer vision, ornithologists, and ecol-ogists. Code and the link to the dataset is available at https://github.com/airou-lab/3D_Multi_Bird_Tracking.

Multipath TCP (MPTCP) has been widely used as an efficient way for communication in many applications.Data centers, smartphones, and network operators use MPTCP to balance the traffic in a network efficiently.MPTCP is an extension of TCP (Transmission Control Protocol), which provides multiple paths, leading to higher throughput and low latency.Although MPTCP has shown better performance than TCP in many applications, it has its own challenges.The network can become congested due to heavy traffic in the multiple paths (subflows) if the subflow rates are not determined correctly.Moreover, communication latency can occur if the packets are not scheduled correctly between the subflows.This paper reviews techniques to solve the above-mentioned problems based on two main approaches; non data-driven (classical) and data-driven (Machine Learning) approaches.This paper compares these two approaches and highlights their strengths and weaknesses with a view to motivating future researchers in this exciting area of machine learning for communications.This paper also provides details on the simulation of MPTCP and its implementations in real environments.

A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents. In particular, each agent perceives the environment as effectively non-stationary due to the changing policies of other agents. Moreover, each agent is itself constantly learning, leading to natural non-stationarity in the distribution of experiences encountered. In this paper, we propose a novel meta-multiagent policy gradient theorem that directly accounts for the non-stationary policy dynamics inherent to multiagent learning settings. This is achieved by modeling our gradient updates to consider both an agent’s own non-stationary policy dynamics and the non-stationary policy dynamics of other agents in the environment. We show that our theoretically grounded approach provides a general solution to the multiagent learning problem, which inherently comprises all key aspects of previous state of the art approaches on this topic. We test our method on a diverse suite of multiagent benchmarks and demonstrate a more efficient ability to adapt to new agents as they learn than baseline methods across the full spectrum of mixed incentive, competitive, and cooperative domains.

Neural Networks (NNs) can provide major empirical performance improvements for robotic systems, but they also introduce challenges in formally analyzing those systems’ safety properties. In particular, this work focuses on estimating the forward reachable set of closed-loop systems with NN controllers. Recent work provides bounds on these reachable sets, yet the computationally efficient approaches provide overly conservative bounds (thus cannot be used to verify useful properties), whereas tighter methods are too intensive for online computation. This work bridges the gap by formulating a convex optimization problem for reachability analysis for closed-loop systems with NN controllers. While the solutions are less tight than prior semidefinite program-based methods, they are substantially faster to compute, and some of the available computation time can be used to refine the bounds through input set partitioning, which more than overcomes the tightness gap. The proposed framework further considers systems with measurement and process noise, thus being applicable to realistic systems with uncertainty. Finally, numerical comparisons show that our approach based on linear programming and partitioning can give 10× reduction in conservatism in $\frac{1}{2}$ of the computation time compared to the state-of-the-art, and the ability to handle various sources of uncertainty is highlighted on a quadrotor model.

One desirable capability of autonomous cars is to accurately predict the pedestrian motion near intersections for safe and efficient trajectory planning. We are interested in developing transfer learning algorithms that can be trained on the pedestrian trajectories collected at one intersection and yet still provide accurate predictions of the trajectories at another, previously unseen intersection. We first discussed the feature selection for transferable pedestrian motion models in general. Following this discussion, we developed one transferable pedestrian motion prediction algorithm based on Inverse Reinforcement Learning (IRL) that infers pedestrian intentions and predicts future trajectories based on observed trajectory. We evaluated our algorithm at three intersections. We used the accuracy of augmented semi-nonnegative sparse coding (ASNSC), trained and tested at the same intersection as a baseline. The result shows that the proposed algorithm improves the baseline accuracy by a statistically significant percentage in both non-transfer task and transfer task.

Place recognition is an essential part of robot localization and mapping problems. Using lower data-rate sensors like 2D scanning laser rangefinders enables the robots to use less memory and computation in building maps. However, place recognition by a vehicle with 6-DOF dynamics like a quadrotor in unstructured, 3D environments like forests is challenging, especially with a sensor that only measures a planar slice of the environment. This paper extends the 2D geometry-based place recognition system of [1] to a challenging forest envirnoment with a novel procedure for selecting stable and salient 2D laser interest points using Dirichlet process clustering (DP-means). This method is tested on both synthetic and real data from a forest trail and compared with [1]. The result reveals the importance of salient interest point selection in allowing accurate and fast place recognition. Our approach also ensures a low bandwidth representation of visited areas, making it suitable for real-time, multi-agent SLAM applications.

This paper presents four distributed motion controllers to enable a group of robots to collectively transport an object towards a guide robot. These controllers include: rotation around a pivot robot, rotation in-place around an estimated centroid of the object, translation, and a combined motion of rotation and translation in which each manipulating robot follows a trochoid path. Three of these controllers require an estimate of the centroid of the object, to use as the axis of rotation. Assuming the object is surrounded by manipulator robots, we approximate the centroid of the object by measuring the centroid of the manipulating robots. Our algorithms and controllers are fully distributed and robust to changes in network topology, robot population, and sensor error. We tested all of the algorithms in real-world environments with 9 robots, and show that the error of the centroid estimation is low, and that all four controllers produce reliable motion of the object.

Multi-robot manipulation allows for scalable environmental interaction, which is critical for multi-robot systems to have an impact on our world. A successful manipulation model requires cost-effective robots, robust hardware, and proper system feedback and control. This paper details key sensing and manipulator capabilities of the r-one robot. The r-one robot is an advanced, open source, low-cost platform for multi-robot manipulation and sensing that meets all of these requirements. The parts cost is around $250 per robot. The r-one has a rich sensor suite, including a flexible IR communication/localization/obstacle detection system, high-precision quadrature encoders, gyroscope, accelerometer, integrated bump sensor, and light sensors. Two years of working with these robots inspired the development of an external manipulator that gives the robots the ability to interact with their environment. This paper presents an overview of the r-one, the r-one manipulator, and basic manipulation experiments to illustrate the efficacy our design. The advanced design, low cost, and small size can support university research with large populations of robots and multi-robot curriculum in computer science, electrical engineering, and mechanical engineering. We conclude with remarks on the future implementation of the manipulators and expected work to follow.

Roboticists, biologists, and chemists are now producing large populations of simple robots, but controlling large populations of robots with limited capabilities is difficult, due to communication and onboard-computation constraints. Direct human control of large populations seems even more challenging. In this paper we investigate control of mobile robots that move in a 2D workspace using three different system models. We focus on a model that uses broadcast control inputs specified in the global reference frame. In an obstacle-free workspace this system model is uncontrollable because it has only two controllable degrees of freedom - all robots receive the same inputs and move uniformly. We prove that adding a single obstacle can make the system controllable, for any number of robots. We provide a position control algorithm, and demonstrate through extensive testing with human subjects that many manipulation tasks can be reliably completed, even by novice users, under this system model, with performance benefits compared to the alternate models. We compare the sensing, computation, communication, time, and bandwidth costs for all three system models. Results are validated with extensive simulations and hardware experiments using over 100 robots.

A new motion planning algorithm is proposed for point and disc robots. In this approach, the problem is first formulated as a Binary Integer Programming with variables taken from Delaunay Triangulation of the 2D or n-D Free Configuration Space, and then transformed into LMIs and solved to obtain an optimal channel made of connected triangles. The channel is then used to build safe and short paths within from Start to Goal. It is also possible to weight certain passageways of the space so that the robot can avoid costly routes, which is especially useful for traffic control applications. Finally, a tracking control strategy along trajectory based on preplanned path is applied for a synchronous drive robot. The algorithm is simple, complete, and does not suffer from local minima. It is also extendable to 3 and higher C-spaces.