Nadeesha Ranasinghe

A system for in-space assembly

This paper presents an experimental system for assembly in space. A weightless and frictionless environment is approximated using an air-hockey table where robots and structural components can float on the surface. The robots use fan propulsion to dock with components and assemble them together to make 2D structures. This system is designed to implement three key technologies for space self-assembly: 1) intelligent components with universal connectors, 2) a set of self-reconfigurable robots that fetch and assemble components, and 3) a distributed method for controlling the robotic-assembly process. An overview of the systems design and experimental results is presented.

Wheeled locomotion for payload carrying with modular robot

Carrying heavy payloads is a challenging task for the modular robot, because its composing modules are relatively tiny and less strong compared with conventional robots. To accomplish this task, we attached passive rollers to the modular robot, and designed a wheeled locomotion gait called tricycleBot. The gait is inspired by paddling motion, and is implemented on the modular robot called SuperBot. Features of this gait are systematically studied and verified through extensive experiments. It is shown that tricycleBot can carry payloads at least 530% of its own weight. It can also be steered remotely to move forward/backward, turn left/right. Capability of tricycleBot demonstrates that the versatility of modular robot can be further expanded to solve very specialized and challenging tasks by using heterogeneous devices.

Surprise-based developmental learning and experimental results on robots

Learning from surprises and unexpected situations is a capability that is critical for developmental learning. This paper describes a promising approach in which a learner robot engages in a cyclic learning process consisting of “prediction, action, observation, analysis (of surprise) and adaptation”. In particular, the robot always predicts the consequences of its actions, detects surprises whenever there is a significant discrepancy between the prediction and the observed reality, analyzes the surprises for causes, and uses the analyzed knowledge to adapt to the unexpected situations. We tested this approach on a modular robot learning how to navigate and recover from unexpected changes in sensors, actions, goals, and environments. The results are very encouraging.

An online gait adaptation with SuperBot in sloped terrains

Among the different types of robots, modular and self-reconfigurable robots such as SuperBot have less limitations than their counterparts due to their versatility of gaits and increased dynamic adaptability. This results in a highly dexterous and adjustable robot suitable for many environments. This however, usually comes at the expense of a necessary human observer required to monitor and control the robot manually resulting in a waste of power and time. Thus, an intelligent system would be indispensable in optimzing the behavior and control of modular and self-reconfigurable robots. This paper presents an Intelligent Online Reconfiguration System (IORS) which through a combination of learning and reasoning, increases the efficiency in control and movement of the modular and self-reconfigurable robot called Superbot. Using this system, Superbot is able to learn and choose the best gait automatically by sensing its current environment (e.g., friction or slope). As a result, the IORS implementation in SuperBot achieves: 1) correct slope gradient sensing, 2) best gait learning to traverse different slopes, and 3) rational decision making for choosing the best gait.

ReMod3D: A high-performance simulator for autonomous, self-reconfigurable robots

Three-dimensional, physics-based simulators are important to the field of self-reconfigurable robotics because they allow researchers to approximate the physical interactions and autonomous behaviors of large numbers of modules in a low-cost, safe, and highly-controlled manner. This paper presents a novel, high-performance, general-purpose simulator for autonomous, self-reconfigurable robots called ReMod3D (RM3D) that overcomes the speed and scalability limitations of existing self-reconfigurable simulators while, at the same time, allowing for realistic module structures, complex environments, and high physical simulation fidelity. While most existing self-reconfigurable simulators view modules as actuated physical bodies with programmable controllers, RM3D views them as embodied agents, defined not only by their physical bodies (links, joints, docks, sensors, actuators) but also by their minds (actions, percepts, behaviors, world models) and the noise inherent in the interaction between sensors, actuators, and the environment. RM3D also simulates inter-module dock connection breakage, something novel for self-reconfigurable robot simulators. Additionally, we present experimental evidence showing that this novel architecture makes RM3D well-suited to locomotion, manipulation, reconfiguration, and embodied intelligence research.

Autonomous Surveillance Tolerant to Interference

Autonomous recognition of human activities from video streams is an important aspect of surveillance. A key challenge is to learn an appropriate representation or model of each activity. This paper presents a novel solution for recognizing a set of predefined actions in video streams of variable durations, even in the presence of interference, such as noise and gaps caused by occlusions or intermittent data loss. The most significant contribution of this solution is learning the number of states required to represent an action, in a short period of time, without exhaustive testing of all state spaces. It works by using Surprise-Based Learning (SBL) to reason on data (object tracks) provided by a vision module. SBL autonomously learns a set of rules which capture the essential information required to disambiguate each action. These rules are then grouped together to form states and a corresponding Markov chain which can detect actions with varying time duration. Several experiments on the publicly available visint.org video corpora have yielded favorable results.

Multifunctional behaviors of reconfigurable superbot robots

Superbot consists of Lego-like but autonomous robotic modules that can reconfigure into different systems for different tasks. Examples of configurable systems include rolling tracks or wheels (for efficient travel), spiders or centipedes (for climbing), snakes (for burrowing in ground), and climbers (for inspection and repair in space). This video shows several configurations and behaviors that are new for modular and reconfigurable robots. Each SuperBot module is a complete robotic system and has a power supply, micro- controllers, sensors, communication, three degrees of freedom, and six connecting faces (front, back, left, right, up and down) to dynamically connect to other modules. This design allows flexible bending, docking, and continuous rotation. A single module can move forward, back, left, right, flip-over, and rotate as a wheel. Modules can communication with each other for totally distributed control and can support arbitrary module reshuffling during their operation. The modules have both internal and external sensors for monitoring self-status and environmental parameters. They can form arbitrary configurations (graphs) and can control these configurations for different functionality such as locomotion, manipulation, and self-repair. This video shows the latest status the SuperBot modules and all these behaviors were made in just one week. The fact that SuperBot can achieve so much in so short a time demonstrates the unique value of modular, multifunctional and self-reconfigurable robots.

BioAIR: Bio-inspired airborne infrastructure reconfiguration

Maintaining constant communication between mobile entities distributed across a large geographical area is a crucial task for many commercial and military applications. For example when troops are deployed in hostile or sensor deprived environments, maintaining radio contact with a base station would increase the efficiency of coordinating the deployment, yet maintaining communications should not interfere with the primary tasks of these entities. The BioAIR system was developed to coordinate airborne communication nodes such as unmanned aerial vehicles (UAV) in order to autonomously form and maintain a dynamic communication network. This system draws upon inspirations from biological cell differentiation through hormone based communication to coordinate a swarm of airborne nodes in a distributed manner by mapping the radio signals into digital hormones. BioAIR offers three primary capabilities, namely collaborative communication, sensing and navigation. BioAIR performs collaborative communication by autonomously creating a mobile ad-hoc network. This network connects several designated nodes by strategically positioning other nodes based on the desired communication signal quality between them. BioAIR performs collaborative sensing by autonomously reinforcing critical locations based on network traffic, detecting any damage to the formed network, and self-repairing. Additionally, BioAIR can coordinate the sensing effort of possibly heterogeneous sensors distributed amongst all nodes in the network to form a distributed sensor network. BioAIR performs collaborative navigation by following the motion of designated nodes while maintaining the formed communication network, provided that the nodes can react fast enough.

BioAIM: Bio-inspired Autonomous Infrastructure Monitoring

The Bio-inspired Autonomous Infrastructure Monitoring (BioAIM) system detects anomalous behavior during the deployment and maintenance of a wireless communication network formed autonomously by unmanned airborne nodes. A node may experience anomalous or unexpected behavior in the presence of hardware/software faults/failures, or external influence (e.g. natural weather phenomena, enemy threats). This system autonomously detects, reasons with (e.g. differentiates an anomaly from natural interference), and alerts a human operator of anomalies at runtime via a communication network formed by the Bio-inspired Artificial Intelligence Reconfiguration (BioAIR) system. In particular, BioAIM learns and builds a prediction model which describes how data from relevant sensors should change when a behavior executes under normal circumstances. Surprises occur when there are discrepancies between what is predicted and what is observed. BioAIM identifies a dynamic set of states from the prediction model and learns a structured model similar to a Markov Chain in order to quantify the magnitude of a surprise or divergence from the norm using a special similarity metric. While in operation BioAIM monitors the sensor data by testing the applicable models for each valid behavior at regular time intervals, and informs the operator when a similarity metric deviates from the acceptable threshold.