Cambrian Intelligence: The Early History of the New AI

This paper describes a general passivity-based framework for the control of flexible joint robots. Recent results on torque, position, as well as impedance control of flexible joint robots are summarized, and the relations between the individual contributions are highlighted. It is shown that an inner torque feedback loop can be incorporated into a passivity-based analysis by interpreting torque feedback in terms of shaping of the motor inertia. This result, which implicitly was already included in earlier work on torque and position control, can also be used for the design of impedance controllers. For impedance control, furthermore, potential energy shaping is of special interest. It is shown how, based only on the motor angles, a potential function can be designed which simultaneously incorporates gravity compensation and a desired Cartesian stiffness relation for the link angles. All the presented controllers were experimentally evaluated on DLR lightweight robots and their performance and robustness shown with respect to uncertain model parameters. Experimental results with position controllers as well as an impact experiment are presented briefly, and an overview of several applications is given in which the controllers have been applied.

A Unified Passivity Based Control Framework for Position, Torque and Impedance Control of Flexible Joint Robots.

This paper is concerned of the loop closure detection problem for visual simultaneous localization and mapping systems. We propose a novel approach based on the stacked denoising auto-encoder (SDA), a multi-layer neural network that autonomously learns an compressed representation from the raw input data in an unsupervised way. Different with the traditional bag-of-words based methods, the deep network has the ability to learn the complex inner structures in image data, while no longer needs to manually design the visual features. Our approach employs the characteristics of the SDA to solve the loop detection problem. The workflow of training the network, utilizing the features and computing the similarity score is presented. The performance of SDA is evaluated by a comparison study with Fab-map 2.0 using data from open datasets and physical robots. The results show that SDA is feasible for detecting loops at a satisfactory precision and can therefore provide an alternative way for visual SLAM systems.

Unsupervised learning to detect loops using deep neural networks for visual SLAM system

Cooperative parallel particle filters for online model selection and applications to urban mobility

The perception-driven approach and end-to-end system are two major vision-based frameworks for self-driving cars. However, it is difficult to introduce attention and historical information into the autonomous driving process, which are essential for achieving human-like driving in these two methods. In this paper, we propose a novel model for self-driving cars called the brain-inspired cognitive model with attention. This model comprises three parts: 1) a convolutional neural network for simulating the human visual cortex; 2) a cognitive map to describe the relationships between objects in a complex traffic scene; and 3) a recurrent neural network, which is combined with the real-time updated cognitive map to implement the attention mechanism and long-short term memory. An advantage of our model is that it can accurately solve three tasks simultaneously: 1) detecting the free space and boundaries for the current and adjacent lanes; 2) estimating the distances to obstacles and vehicle attitude; and 3) learning the driving behavior and decision-making process of a human driver. Importantly, the proposed model can accept external navigation instructions during an end-to-end driving process. To evaluate the model, we built a large-scale road-vehicle dataset containing over 40 000 labeled road images captured by three cameras placed on our self-driving car. Moreover, human driving activities and vehicle states were recorded at the same time.

Brain-Inspired Cognitive Model With Attention for Self-Driving Cars

This paper describes a cognitive map building and navigation system using an RGB-D sensor for mobile robots. A brain-inspired simultaneously localization and mapping (SLAM) system, that requires raw odometry data and RGB-D information, is used to construct a spatial cognitive map of an office environment. The cognitive map contains a set of spatial coordinates that the robot has traveled. A global path is extracted from the built cognitive map and subsequently used by a local planner to instruct the robot to navigate. The global path is a subset of the path that builds up the cognitive map. This is different from other path planning mechanisms that construct a path based on a ground-truth map. Experiment results show that the employment of the RGB-D sensor significantly improves the mapping results.

/pdf/rgb-d-based-cognitive-map-building-and-navigation-bc60qgzihf.pdf

RGB-D based cognitive map building and navigation

Hippocampal place cells and entorhinal grid cells have been hypothesized to be able to form map-like spatial representation of the environment, namely cognitive map. In most prior approaches, either neural network methods or only hippocampal models are used for building cognitive maps, lacking biological fidelity to the entorhinal-hippocampal system. This paper presents a novel computational model to build cognitive maps of real environments using both place cells and grid cells. The proposed model includes two major components: (1) A competitive Hebbian learning algorithm is used to select velocity-coupled grid cell population activities, which path-integrate self-motion signals to determine computation of place cell population activities; (2) Visual cues of environments are used to correct the accumulative errors intrinsically associated with the path integration process. Experiments performed on a mobile robot show that cognitive maps of the real environment can be efficiently built. The proposed model would provide an alternative neuro-inspired approach for robotic mapping, navigation and localization.

https://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/download/9420/9298

An entorhinal-hippocampal model for simultaneous cognitive map building

Building an integrated mobile robot that can navigate freely and deliberately in an indoor environment is a challenging task. In this paper, we propose a direction-driven navigation system, in which a mobile robot is instructed to follow the given directions instead of a global path. This is similar to humans when travelling to a target destination by following the directional guidance from someone else. This system consists of two main modules including a grid-based direction planner and a multilayered asymmetrical local navigation module. The directions of movement are computed from a brain-inspired spatial cognitive map using the grid-based direction planner, while the motion of the robot is controlled by the local navigation module. In order to improve the mapping performance using RGB-D input, an improved template comparison method is suggested. The proposed system is implemented in a mobile robot that performs simultaneous localization, mapping, and navigation in a typical office environment. The experimental results indicate that the robot can efficiently navigate to target destinations.

Direction-driven navigation using cognitive map for mobile robots

This paper presents a novel approach employing nonlinear control for stabilization of standing posture for a humanoid robot using only hip joint. The robot is modeled as an acrobot where model parameters are estimated through adaptive algorithm. A `non-collocated partial feedback' controller is applied. This is integrated with a linear feedback control, through LQR. Improved robustness to external push is demonstrated through evaluation in Webots simulator and on a physical humanoid robot, NUSBIP-III ASLAN. Performance comparison with other controllers verifies the effectiveness of the proposed control system.

Standing posture modeling and control for a humanoid robot

This paper presents a brain inspired neural architecture with spatial cognition and navigation capability The brain inspired system is mainly composed of two parts: a bio-inspired hierarchical vision architecture (HMAX) and a hippocampal-like circuitry The HMAX encodes vision inputs as neural activities and maps to hippocampal-like circuitry which stores this information Sensing a similar neural activity pattern this information can be recalled The system is tested on a mobile robot which is placed in a spatial memory task Among the regions in hippocampus, CA1 has place dependance response With this property, the hippocampal-like circuitry stores the goal location according to the vision pattern, and recalls it when a similar vision pattern is seen again The place dependent pattern of CA1 guides the motor neuronal area which then dictates the robot move to the goal location The result of our current study indicates a possible way of connection between hippocampus and vision system, which will help robots perform a rodent-like behavior in the end

Bo Tian

Papers

RGB-D based cognitive map building and navigation

An entorhinal-hippocampal model for simultaneous cognitive map building

Direction-driven navigation using cognitive map for mobile robots

Standing posture modeling and control for a humanoid robot

A neuro-cognitive system and its application in robotics