"Inspired by birds flying through cluttered environments such as dense forests, this paper studies the theoretical foundations of a novel motion planning problem: high-speed navigation through a randomly-generated obstacle field when only the statistics of the obstacle generating process are known a priori. Resembling a planar forest environment, the obstacle generating process is assumed to determine the locations and sizes of disk-shaped obstacles. When this process is ergodic, and under mild technical conditions on the dynamics of the bird, it is shown that the existence of an infinite collision-free trajectory through the forest exhibits a phase transition. On one hand, if the bird flies faster than a certain critical speed, then, with probability one, there is no infinite collision-free trajectory, i.e., the bird will eventually collide with some tree, almost surely, regardless of the planning algorithm governing the bird's motion. On the other hand, if the bird flies slower than this critical speed, then there exists at least one infinite collision-free trajectory, almost surely. Lower and upper bounds on the critical speed are derived for the special case of a homogeneous Poisson forest considering a simple model for the bird's dynamics. For the same case, an equivalent percolation model is provided. Using this model, the phase diagram is approximated in Monte-Carlo simulations. This paper also establishes novel connections between robot motion planning and statistical physics through ergodic theory and percolation theory, which may be of independent interest."

"This paper develops generalizations of empowerment to continuous states. Empowerment is a recently introduced information-theoretic quantity motivated by hypotheses about the efficiency of the sensorimotor loop in biological organisms, but also from considerations stemming from curiosity-driven learning. Empowemerment measures, for agent-environment systems with stochastic transitions, how much influence an agent has on its environment, but only that influence that can be sensed by the agent sensors. It is an information-theoretic generalization of joint controllability (influence on environment) and observability (measurement by sensors) of the environment by the agent, both controllability and observability being usually defined in control theory as the dimensionality of the control/observation spaces.…"

"We introduce the optimal obstacle placement with disambiguations problem wherein the goal is to place true obstacles in an environment cluttered with false obstacles so as to maximize the total traversal length of a navigating agent (NAVA). Prior to the traversal, NAVA is given location information and probabilistic estimates of each disk-shaped hindrance (hereinafter referred to as disk) being a true obstacle. The NAVA can disambiguate a disk's status only when situated on its boundary. There exists an obstacle placing agent (OPA) that locates obstacles prior to NAVA's traversal. The goal of OPA is to place true obstacles in between the clutter in such a way that NAVA's traversal length is maximized in a game-theoretic sense.…"

"We propose distributed algorithms to automatically deploy a team of mobile robots to partition and provide coverage of a non-convex environment. To handle arbitrary non-convex environments, we represent them as graphs. Our partitioning and coverage algorithm requires only short-range, unreliable pairwise "gossip" communication. The algorithm has two components: (1) a motion protocol to ensure that neighboring robots communicate at least sporadically, and (2) a pairwise partitioning rule to update territory ownership when two robots communicate. By studying an appropriate dynamical system on the space of partitions of the graph vertices, we prove that territory ownership converges to a pairwise-optimal partition in finite time. This new equilibrium set represents improved performance over common Lloyd-type algorithms. Additionally, we detail how our algorithm scales well for large teams in large environments and how the computation can run in anytime with limited resources. Finally, we report on large-scale simulations in complex environments and hardware experiments using the Player/Stage robot control system."

"With the aim of producing a stable human-like bipedal gait, a five-link planar walking mechanism is coupled with a central pattern generator (CPG) neural network, consisting of units based on Matsuoka's half-center oscillator model with a firm basis in neurophysiology. As a minimalistic approach to bipedal walking, this type of walking mechanism contains only four actuators, and is lacking feet and ankles. The mechanism is simulated with accurate physics, allowing realistic fitness evaluations for the creation of CPG controllers through evolutionary computation. The oscillatory parameters, internal connectivity structure, and external feedback pathways of the networks are determined through genetic algorithms (GA) optimization. The evolved CPG networks are transferred to a hardware implementation of the mechanism, to test their performance under real-world dynamics. Results confirm that the biologically inspired CPG model is very well suited for controlling legged locomotion, since a diverse manifestation of CPG networks (with and without external feedback) have been observed to succeed during the course of GA evaluations. Observations also imply that while the CPG mechanism is inherently able to sustain a stable gait, the utilization of feedback pathways makes the gait more human-like and is needed to provide a means to adapt to irregularities in the environment."

"I'm jealous of high school computer science students these days. I had to tap out my GOTO 10 commands on a crappy CRT monitor; they get a cheap, rugged robot to play with. The Finch, as it's called, costs just $99, so every student in a classroom can have their own. And its design was rigorously based on educational research that uncovered the five key attributes to making the perfect educational toy."

It's called the DLR Hand Arm System. It has an anthropomorphic design and packs 52 motors, ultra-miniaturized control electronics, a supercapacitor-based power supply, and a web of high-strength tendons. But what makes it stand out compared to conventional systems is its ability to withstand collisions, thanks to ingeniously designed joints and actuators that can absorb and dissipate energy, much like our own arms and hands do.

"Recovering the 3D structure of the scene from images yields useful information for tasks such as shape and scene recognition, object detection, or motion planning and object grasping in robotics. In this thesis, we introduce a general machine learning approach called unsupervised CRF learning based on maximizing the conditional likelihood. We apply our approach to computer vision systems that recover the 3-D scene geometry from images. We focus on recovering 3D geometry from single images, stereo pairs and video sequences. Building these systems requires algorithms for doing inference as well as learning the parameters of conditional Markov random fields (MRF). Our system is trained unsupervisedly without using ground-truth labeled data.…"

"In this paper, a simple Neural controller has been used to achieve stable walking in a NAO biped robot, with 22 degrees of freedom that implemented in a virtual physics-based simulation environment of Robocup soccer simulation environment. The algorithm uses a Matsuoka base neural oscillator to generate control signal for the biped robot. To find the best angular trajectory and optimize network parameters, a new population-based search algorithm, called the Harmony Search (HS) algorithm, has been used. The algorithm conceptualized a group of musicians together trying to search for better state of harmony. Simulation results demonstrate that the modification of the step period and the walking motion due to the sensory feedback signals improves the stability of the walking motion."

"This paper is concerned with designing self-driven fitness functions for Embedded Evolutionary Robotics. The proposed approach considers the entropy of the sensori-motor stream generated by the robot controller. This entropy is computed using unsupervised learning; its maximization, achieved by an on-board evolutionary algorithm, implements a "curiosity instinct", favouring controllers visiting many diverse sensori-motor states (sms). Further, the set of sms discovered by an individual can be transmitted to its offspring, making a cultural evolution mode possible. Cumulative entropy (computed from ancestors and current individual visits to the sms) defines another self-driven fitness; its optimization implements a "discovery instinct", as it favours controllers visiting new or rare sensori-motor states. Empirical results on the benchmark problems proposed by Lehman and Stanley (2008) comparatively demonstrate the merits of the approach."

"During the last decade, incremental sampling-based motion planning algorithms, such as the Rapidly-exploring Random Trees (RRTs) have been shown to work well in practice and to possess theoretical guarantees such as probabilistic completeness. However, no theoretical bounds on the quality of the solution obtained by these algorithms have been established so far. The first contribution of this paper is a negative result: it is proven that, under mild technical conditions, the cost of the best path in the RRT converges almost surely to a non-optimal value. Second, a new algorithm is considered, called the Rapidly-exploring Random Graph (RRG), and it is shown that the cost of the best path in the RRG converges to the optimum almost surely. Third, a tree version of RRG is introduced, called the RRT$^*$ algorithm, which preserves the asymptotic optimality of RRG while maintaining a tree structure like RRT.…"

[Watch the video] "The sensor meanwhile detects surrounding pH levels--the higher the pH concentration, the faster the electromagnetic pulses emitted by the micro-machine. The external computer uses these signals to direct a swarm of about 3,000 magnetically-sensitive bacteria, which push the micro-machine around as it pulses. The bacteria push the micro-machine closer to the higher pH concentration."

Those consequences, as I have considered them, are astounding.

It starts with saving a million young lives every year (45,000 in the USA) as well as untold injury in suffering.
It saves trillions of dollars wasted over congestion, accidents and time spent driving.
Robocars can solve the battery problem of the electric car, making the electric car attractive and inexpensive. They can do the same for many other alternate fuels, too.
Electric cars are cheap, simple and efficient once you solve the battery/range problems.
Switching most urban driving to electric cars, especially ultralight short-trip vehicles means a dramatic reduction in energy demand and pollution.
It could be enough to wean the USA off of foreign oil, with all the change that entails.
It means rethinking cities and manufacturing.
It means the death of old-style mass transit.

We were talking about the Uncanny Valley a few days ago, and I was reminded of Hod's dreaming spider robots, twitching in their sleep.

The world wants to be uncanny and disturbing. I want it to be, and being of the world... I get to say. More of these. Now! With seven legs! And undulating cilia! But it needs more eyes.

And then Pink Floyd plays...?

"The AIST's handles also have hidden 2D barcodes that are visible to robots with infrared vision, telling them exactly how to use it."

Simon Fraser's BEAM robotic projects

Now that's a Robotic Overlord I can happily play minion to.