Model generalization of the underlying dynamics is critical for achieving data efficiency when learning for robot control. This paper proposes a novel approach for learning dynamics leveraging the symmetry in the underlying robotic system, which allows for robust extrapolation from fewer samples. Existing frameworks that represent all data in vector space fail to consider the structured information of the robot, such as leg symmetry, rotational symmetry, and physics invariance. As a result, these schemes require vast amounts of training data to learn the system's redundant elements because they are learned independently. Instead, we propose considering the geometric prior by representing the system in symmetrical object groups and designing neural network architecture to assess invariance and equivariance between the objects. Finally, we demonstrate the effectiveness of our approach by comparing the generalization to unseen data of the proposed model and the existing models. We also implement a controller of a climbing robot based on learned inverse dynamics models. The results show that our method generates accurate control inputs that help the robot reach the desired state while requiring less training data than existing methods.

Perception and interpretation of the terrain is essential for robot navigation, particularly in off-road areas, where terrain characteristics can be highly variable. When planning a path, features such as the terrain gradient and roughness should be considered, and they can jointly represent the traversability cost of the terrain. Despite this range of contributing factors, most cost maps are currently binary in nature, solely indicating traversible versus non-traversible areas. This work presents a joint local and global planning methodology for building continuous cost maps using LIDAR, based on a novel traversability representation of the environment. We investigate two approaches. The first, a statistical approach, computes terrain cost directly from the point cloud. The second, a learning-based approach, predicts an IMU response solely from geometric point cloud data using a 2D-Convolutional-LSTM neural network. This allows us to estimate the cost of a patch without directly driving over it, based on a data set that maps IMU signals to point cloud patches. Based on the terrain analysis, two continuous cost maps are generated to jointly select the optimal path considering distance and traversability cost for local navigation. We present a real-time terrain analysis strategy applicable for local planning, and furthermore demonstrate the straightforward application of the same approach in batch mode for global planning. Off-road autonomous driving experiments in a large and hybrid site illustrate the applicability of the method. We have made the code available online for users to test the method.

Understanding the kinematics of a ground robot is essential for efficient navigation. Based on the kinematic model of a robot, its full motion capabilities can be represented by theoretical motion primitives. However, depending on the environment and/or human preferences, not all of those theoretical motion primitives are desirable and/or achievable. This work presents a method to identify effective motion primitives (eMP) from continuous trajectories for autonomous ground robots. The pipeline efficiently performs segmentation, representation and reconstruction of the motion primitives, using initial human-driving behaviour as a guide to create a motion primitive library. Hence, this strategy incorporates how the environment affects the robot operation regarding accelerations, speed, braking, and steering behaviours.The method is thoroughly tested on an autonomous car-like electric vehicle, and the results show excellent generalisation of the theoretical motion primitive distribution to real vehicle. The experiments are carried out on large site with very diverse characteristics, illustrating the applicability of the method.

This paper proposes a novel configurable wheel that exhibits desired properties of varied radius wheels. Positional manipulation of the centre hub is proposed and tested to achieve these desired characteristics of `virtual' wheels in a physical system. The centre hub is manipulated via the use of pneumatic actuators mounted to and constricted by the outer rim of the wheel, which allows for fast and accurate control to enable the vehicle ride height and gear ratio to be adjusted continuously and be maintained during the wheels' full rotation. Experiments are presented, validating this ability of the system. We envision uses for this system to extend from off-road robotics to space exploration as these wheels exhibit novel characteristics not demonstrated by other platforms.

In this paper we present the design and control strategies of a novel quadruped climbing robot (named Magneto) with three degrees of freedom (3-DOF) actuated limbs and a 3-DOF compliant magnetic foot. By exploiting its high degrees of freedom, Magneto is able to deform its body shape to squeeze through gaps of 23cm, which is smaller than standard human entry portholes of industrial confined spaces. Its compact foot design of footprint 4cm allows Magneto to walk on narrow beams of thickness less than 5cm, even at varying separation. The inherent high dimensional system design enables the body to be positioned in a wide range of orientations and seamlessly switch a limb function from locomotion to manipulation mode mid-climb. This capability enables access to confined space openings and occluded pockets and navigation through complex 3-D structures previously not demonstrated on legged climbing robots.

To address the goal of locomotion in very complex and difficult terrains, the authors are developing a new class of Ultralight Legged Robots. This paper presents the Multilegged Autonomous eXplorer (MAX), an ultralight, six-legged robot for traversal and exploration of challenging indoor and outdoor environments. The design of MAX emphasizes a low mass/size ratio, high locomotion efficiency, and high payload capability compared to total system mass. MAX is 2.25 m tall at full height and has a mass of approximately 60 kg, which makes it 5 to 20 times lighter than robots of comparable size. MAX is a research vehicle to explore modelling and control of Ultralight Legged Robots subject to flexing, oscillations and swaying; algorithms for gait planning and motion planning under uncertainty; and navigation planning for traversal of complex 3D terrains. This paper presents the design of MAX, provides an overview of the control system developed, summarizes results from indoor and outdoor tests, discusses system performance and outlines the challenges to be addressed next.

Jumping is an effective navigation mode for micro-robots. Recent research has addressed significant challenges that exist in developing reliable, energy efficient, light weight micro actuation mechanisms, mostly focused on a single jump. However, there has been limited exploration of planning strategies to enable multi-hop navigation requiring turning and obstacle avoidance. This work introduces the concept of differential jump, generated by asymmetrical thrust from multiple thrusters, as a viable mode for navigation in micro-robots to enable turning during a jump. We present a simplified differential jump model, derive state propagation equations and adapt a sampling based motion planner to compute trajectories for such a system among obstacles in simulation. We further present an early prototype of a micro-robot (≈ 70mm cube) capable of navigation on a planar surface among obstacles using the differential jump mechanism presented.

In a mixed environment of autonomous driverless vehicles and human driven vehicles operating on the same road, identifying intentions of human drivers and interacting with them in a compliant and responsible manner becomes a challenging problem for the driverless vehicles. In this paper, the problem of vehicle interaction at an intersection merging scenario is formulated as an Intention-Aware motion planning problem using the tools from Mixed Observability Markov Decision Process (MOMDP). We utilize the tools from recent intention aware planning framework to demonstrate a merging behavior in the presence of human drivers by trying to infer and act according to the intentions of the human drivers. A driver behavior model for T-junction intersections is developed in order to calculate the probabilistic state transition functions of the MOMDP model. With proposed solution, it is demonstrated that using intention aware planning improves performance in comparison to present time to merge approach by lowering accident probability and intersection navigation duration. The proposed method is tested on a real autonomous vehicle (AV) in the presence of human driven vehicles to validate our approach.

This paper proposes a semantic mapping method based on pedestrian activity in the urban road environment. Pedestrian activity patterns are learned from pedestrian tracks collected by a mobile platform. With the learned knowledge of pedestrian activity, semantic mapping is performed using Bayesian classification techniques. The proposed method is tested in real experiments, and shows promising results in recognizing four activity-related semantic properties of the urban road environment: pedestrian path, entrance/exit, pedestrian crossing and sidewalk.

This paper presents a precise localization algorithm for vehicles in 3D urban environment with only one 2D LIDAR and odometry information. A novel idea of synthetic 2D LIDAR is proposed to solve the localization problem on a virtual 2D plane. A Monte Carlo Localization scheme is adopted for vehicle position estimation, based on synthetic LIDAR measurements and odometry information. The accuracy and robustness of the proposed algorithm are demonstrated by performing real time localization in a 1.5 km driving test around the NUS campus area.

In this paper, we report a fully automated detailed mapping of a challenging urban environment using single LIDAR. To improve scan matching, extended correlative scan matcher is proposed. Also, a Monte Carlo loop closure detection is implemented to perform place recognition efficiently. Automatic recovery of the pose graph map in the presence of false place recognition is realized through a heuristic based loop closure rejection. This mapping framework is evaluated through experiments on the real world dataset obtained from NUS campus environment.

This paper presents a method of road detection and mapping using accumulated 3D data from 2D scans. The idea of 3D rolling window is introduced, and its probabilistic characteristics are studied. A cascaded road detection process is developed with region-growing and classification methods. A probabilistic framework is utilized for road mapping purposes with the detection results. The performance of detection and mapping algorithm is evaluated through experiments.

One of the most prominent features on an urban road is the curb, which defines the boundary of a road surface. An intersection is a junction of two or more roads, appearing where no curb exists. The combination of curb and intersection features and their idiosyncrasies carry significant information about the urban road network that can be exploited to improve a vehicle's localization. This paper introduces a Monte Carlo Localization (MCL) method using the curb-intersection features on urban roads. We propose a novel idea of “Virtual LIDAR” to get the measurement models for these features. Under the MCL framework, above road observation is fused with odometry information, which is able to yield precise localization. We implement the system using a single tilted 2D LIDAR on our autonomous test bed and show robust performance in the presence of occlusion from other vehicles and pedestrians.

We present an autonomous vehicle providing mobility-on-demand service in a crowded urban environment. The focus in developing the vehicle has been to attain autonomous driving with minimal sensing and low cost, off-the-shelf sensors to ensure the system's economic viability. The autonomous vehicle has successfully completed over 50 km handling numerous mobility requests during the course of multiple demonstrations. The video provides an overview of our approach, with special comments on our localization and perception modules showcasing one such request being serviced.

We propose a local Voronoi decomposition (LVD) algorithm which is able to perform a robust and online task allocation for multiple agents based purely on local information. Because only local information is required in determining each agent's Voronoi region, each agent can then make its decision in a distributive fashion based on its allocated Voronoi region. These Voronoi regions eliminates the occurrence of agents executing instantaneous overlapping tasks. As our method does not require a pre-processing of the map, it is also able to work well in a dynamically changing map with changing number of agents. We will show our proof of concept in the problem of exploration in an unknown environment. In our experimental evaluation, we show that our method significantly outperforms the competing algorithms: Ants algorithm and the Brick&Mortar algorithm. Our results also show that our method is near the theoretical best solution.

Target tracking among obstacles is an interesting class of motion planning problems that combine the usual motion constraints with robot sensors' visibility constraints. In this paper, we introduce the notion of vantage time and use it to formulate a risk function that evaluates the robot's advantage in maintaining the visibility constraint against the target. Local minimization of the risk function leads to a greedy tracking strategy. We also use simple velocity prediction on the target to further improve tracking performance. We compared our new strategy with earlier work in extensive simulation experiments and obtained much improved results